A computer-aided diagnosis (CAD) system is presented to automatically distinguish normal from abnormal tissue in high-resolution CT chest scans acquired during daily clinical practice. From high-resolution computed tomography scans of 116 patients, 657 regions of interest are extracted that are to be classified as displaying either normal or abnormal lung tissue. A principled texture analysis approach is used, extracting features to describe local image structure by means of a multi-scale filter bank. The use of various classifiers and feature subsets is compared and results are evaluated with ROC analysis. Performance of the system is shown to approach that of two expert radiologists in diagnosing the local regions of interest, with an area under the ROC curve of 0.862 for the CAD scheme versus 0.877 and 0.893 for the radiologists.

Prone MR imaging has no additional value when the supine MR image has clearly shown the cause of tethering or in patients who have undergone tethered cord surgery, but it can provide additional information in patients clinically suspected of having a tethered cord and in whom supine MR imaging depicted no abnormalities.

No abstract

Fourteen critically ill patients underwent percutaneous drainage of abdominal abscesses. All 14 had one or more relative contraindications to external drainage procedure: (a) multiloculated abscesses; (b) multiple abscesses; (c) abscesses that form fistulae to surrounding organs; (d) abscesses containing viscous fluid, debris, or necrotic material. A total of 32 cavities was drained, usually using a multiple trocar/catheter system. Biplane computed tomography demonstrated a safe drainage route in all patients. In those patients in whom the contents of the abscess were too viscous to permit drainage, the contents were liquefied with acetylcysteine. Nine of the 14 patients (64%) recovered completely following the drainage procedure.

In a case of diffuse xanthogranulomatous pyelonephritis, computed tomography (CT) and magnetic resonance (MR) were used. The MR proved to be more precise in the preoperative evaluation of inflammatory extension to the spleen and into the abdominal wall. The CT was more accurate in excluding spread to the colon.