Biomedical subjects

Issam El-Naqa

Publications and source records attributed to Issam El-Naqa.

3 recordsLinked to original sources

PubMed2004

Dosimetric correlates for acute esophagitis in patients treated with radiotherapy for lung carcinoma.

PURPOSE: Acute esophagitis is a common complication of radiotherapy (RT) for non-small-cell carcinoma of the lung. Previous reports have related esophagitis to dosimetric parameters such as the length of the irradiated esophagus, maximal dose, or volume of the organ treated beyond a threshold dose. However, when using oblique beams, a portion of the esophageal circumference may be outside the treated field, resulting in partial esophageal irradiation. Therefore, our aim was to determine whether the irradiated esophageal surface area and/or esophageal volume are predictive of acute esophagitis in relation to other clinical and treatment-related factors. METHODS AND MATERIALS: Complete dose-volume information was gathered for 166 patients receiving definitive RT for Stage I-IIIB non-small-cell carcinoma of the lung at our institution. Seventy-eight patients received chemotherapy (37 before RT and 41 concurrently). All patients were treated to doses of 60-74 Gy (median, 70 Gy) delivered in single daily fractions of 1.8-2.1 Gy. The doses were prescribed to the isocenter without using heterogeneity corrections; however, the doses were corrected to account for lung heterogeneity in this report. Esophageal contrast was used to contour the esophagus from the cricoid to the gastroesophageal junction in each case. Esophagitis was scored according to the Radiation Therapy Oncology Group criteria with Grade 2 or worse considered clinically significant. To determine the importance of the irradiated surface area, the volumetric treatment plan for each patient was prepared for analysis by relating a surface area to each point of the esophagus contour. Spearman's rank correlation was used to correlate the esophagitis score with A(d), where A represents the surface area (in centimeters squared) receiving the dose, d, or greater (in Gray), or V(d), where V represents the volume (in centimeters cubed) receiving d (in Gray). The surface areas studied were A(5)-A(80) or V(5)-V(80) in 5-Gy increments. The clinical parameters studied in univariate analysis included patient age, stage, performance status, use of pretreatment chemotherapy, and use of concurrent chemotherapy. Step-wise regression analysis was then used to determine the statistically significant factors predicting acute esophagitis. RESULTS: Forty-five patients (27%) developed Grade 2 or worse esophagitis, 37 developed Grade 2, 7 Grade 3, and 1 Grade 4. No deaths resulted from this complication. The most statistically significant single parameters for predicting acute esophagitis were A(55), V(60), and the use of concurrent chemotherapy. Age, stage, performance status, and pre-RT chemotherapy had no statistically significant influence on the incidence of acute esophagitis. On logistic regression analysis, A(55) (p < or =0.0005), V(60) (p < or =0.001), and the use of concurrent chemotherapy (p = 0.001) emerged as statistically significant correlates of acute esophagitis. CONCLUSION: The esophageal surface area receiving > or =55 Gy, the esophageal volume receiving > or =60 Gy, and the use of concurrent chemotherapy were the most statistically significant predictive factors for early esophagitis. Adequate dosimetric coverage of the planning target volume remains the goal of RT planning. High values of A(55) and/or V(60) are indicative of the development of acute esophagitis and may indicate a need to explore alternative RT planning options.

Acute Disease↗

PubMed2004

A similarity learning approach to content-based image retrieval: application to digital mammography.

In this paper, we describe an approach to content-based retrieval of medical images from a database, and provide a preliminary demonstration of our approach as applied to retrieval of digital mammograms. Content-based image retrieval (CBIR) refers to the retrieval of images from a database using information derived from the images themselves, rather than solely from accompanying text indices. In the medical-imaging context, the ultimate aim of CBIR is to provide radiologists with a diagnostic aid in the form of a display of relevant past cases, along with proven pathology and other suitable information. CBIR may also be useful as a training tool for medical students and residents. The goal of information retrieval is to recall from a database information that is relevant to the user's query. The most challenging aspect of CBIR is the definition of relevance (similarity), which is used to guide the retrieval machine. In this paper, we pursue a new approach, in which similarity is learned from training examples provided by human observers. Specifically, we explore the use of neural networks and support vector machines to predict the user's notion of similarity. Within this framework we propose using a hierarchal learning approach, which consists of a cascade of a binary classifier and a regression module to optimize retrieval effectiveness and efficiency. We also explore how to incorporate online human interaction to achieve relevance feedback in this learning framework. Our experiments are based on a database consisting of 76 mammograms, all of which contain clustered microcalcifications (MCs). Our goal is to retrieve mammogram images containing similar MC clusters to that in a query. The performance of the retrieval system is evaluated using precision-recall curves computed using a cross-validation procedure. Our experimental results demonstrate that: 1) the learning framework can accurately predict the perceptual similarity reported by human observers, thereby serving as a basis for CBIR; 2) the learning-based framework can significantly outperform a simple distance-based similarity metric; 3) the use of the hierarchical two-stage network can improve retrieval performance; and 4) relevance feedback can be effectively incorporated into this learning framework to achieve improvement in retrieval precision based on online interaction with users; and 5) the retrieved images by the network can have predicting value for the disease condition of the query.

Algorithms↗

PubMed2002

A support vector machine approach for detection of microcalcifications.

In this paper, we investigate an approach based on support vector machines (SVMs) for detection of microcalcification (MC) clusters in digital mammograms, and propose a successive enhancement learning scheme for improved performance. SVM is a machine-learning method, based on the principle of structural risk minimization, which performs well when applied to data outside the training set. We formulate MC detection as a supervised-learning problem and apply SVM to develop the detection algorithm. We use the SVM to detect at each location in the image whether an MC is present or not. We tested the proposed method using a database of 76 clinical mammograms containing 1120 MCs. We use free-response receiver operating characteristic curves to evaluate detection performance, and compare the proposed algorithm with several existing methods. In our experiments, the proposed SVM framework outperformed all the other methods tested. In particular, a sensitivity as high as 94% was achieved by the SVM method at an error rate of one false-positive cluster per image. The ability of SVM to out perform several well-known methods developed for the widely studied problem of MC detection suggests that SVM is a promising technique for object detection in a medical imaging application.

Algorithms↗