Quantitative classification of mammographic parenchyma based on radiological assessment has been shown to provide one of the strongest estimates of the risk of developing breast cancer. Existing classification schemes, however, are limited by coarse category scales. In addition, subjectivity can lead to sizeable interobserver and intraobserver variations. Here, the authors propose an interactive thresholding technique applied to digitized film-screen mammograms, which assesses the proportion of the mammographic image representing radiographically dense tissue. Observers viewed images on a CRT display and selected grey-level thresholds from which the breast and regions of dense tissue in the breast were identified. The proportion of radiographic density was then calculated from the image histogram. The technique was evaluated for the mammograms of 30 women and is well correlated (R>0.91, Spearman coefficient) with a six-category subjective classification of radiographic density by radiologists. The technique was found to be very reliable with an intraclass correlation coefficient between observers typically R>0.9. This technique may have a role in routine mammographic analysis for the purpose of assessing risk categories and as a tool in studies of the etiology of breast cancer, in particular for monitoring changes in breast parenchyma during potential preventive interventions.

https://iopscience.iop.org/article/10.1088/0031-9155/39/10/008/pdf

The quantitative analysis of mammographic densities

The traditional chest radiograph is still ubiquitous in clinical practice, and will likely remain so for quite some time. Yet, its interpretation is notoriously difficult. This explains the continued interest in computer-aided diagnosis for chest radiography. The purpose of this survey is to categorize and briefly review the literature on computer analysis of chest images, which comprises over 150 papers published in the last 30 years. Remaining challenges are indicated and some directions for future research are given.

/pdf/computer-aided-diagnosis-in-chest-radiography-a-survey-2g53b77kmg.pdf

Computer-aided diagnosis in chest radiography: a survey

The present invention relates to methods and systems for conducting three-dimensional image analysis and diagnosis and possible treatment relating thereto. The invention includes methods of handling signals containing information (data) relating to three-dimensional representation of objects scanned by a scanning medium. The invention also includes methods of making and analyzing volumetric measurements and changes in volumetric measurements which can be used for the purpose of diagnosis and treatment.

System and method for three-dimensional image rendering and analysis

We are developing a computer-aided diagnosis (CAD) system for lung nodule detection on thoracic helical computed tomography (CT) images. In the first stage of this CAD system, lung regions are identified by a k-means clustering technique. Each lung slice is classified as belonging to the upper, middle, or the lower part of the lung volume. Within each lung region, structures are segmented again using weighted k-means clustering. These structures may include true lung nodules and normal structures consisting mainly of blood vessels. Rule-based classifiers are designed to distinguish nodules and normal structures using 2D and 3D features. After rule-based classification, linear discriminant analysis (LDA) is used to further reduce the number of false positive (FP) objects. We performed a preliminary study using 1454 CT slices from 34 patients with 63 lung nodules. When only LDA classification was applied to the segmented objects, the sensitivity was 84% (53/63) with 5.48 (7961/1454) FP objects per slice. When rule-based classification was used before LDA, the free response receiver operating characteristic (FROC) curve improved over the entire sensitivity and specificity ranges of interest. In particular, the FP rate decreased to 1.74 (2530/1454) objects per slice at the same sensitivity. Thus, compared to FP reduction with LDA alone, the inclusion of rule-based classification lead to an improvement in detection accuracy for the CAD system. These preliminary results demonstrate the feasibility of our approach to lung nodule detection and FP reduction on CT images.

/pdf/lung-nodule-detection-on-thoracic-computed-tomography-images-je7sh7mim8.pdf

Lung nodule detection on thoracic computed tomography images: Preliminary evaluation of a computer-aided diagnosis system

Cassette-based computed radiography (CR) systems have continued to evolve in parallel with integrated, instant readout digital radiography (DR) systems. The image quality of present day CR systems is approaching its theoretical limits but is significantly inferior to DR. Further improvements in CR image quality require improved concepts. The aim of this review is to identify the fundamental limitations in CR performance. This will provide a background for the development of new approaches to improve photostimulable phosphor CR systems. It will also guide research in designing better CR systems to possibly compete with DR systems in terms of image quality parameters such as detective quantum efficiency and yet maintain CR convenience in being portable and more economical.

https://iopscience.iop.org/article/10.1088/0031-9155/47/23/201/pdf

The physics of computed radiography

Rationale and objectives To reduce the number of false-negative diagnoses by radiologists, the authors are developing a computer-aided diagnosis scheme for detection of lung nodules in digital chest images. In this study, the authors attempted to reduce the number of false-positive diagnoses obtained with a previous computer scheme by incorporating additional knowledge from experienced chest radiologists into the computer scheme. Methods The authors applied their previous computer scheme, using less-strict criteria, to 60 clinical chest radiographs; this yielded 735 candidate nodules (23 true nodules and 712 false-positive diagnoses). These candidates were analyzed using region-growing, trend-correction, and edge-gradient techniques to determine measures by which to quantify image features of candidate nodules. Results The 712 false-positive diagnoses represented various anatomic structures that were located throughout the chest image. From this analysis, we were able to decrease the number of false-positive errors from an average of 12 to approximately 5 per image without eliminating any true nodules. Conclusion Our results show that incorporating knowledge from experienced chest radiologists into the computer algorithm will play an important role in the development of computerized schemes for the detection of pulmonary nodules.

Image feature analysis of false-positive diagnoses produced by automated detection of lung nodules.

A method and system for correcting a non-linear characteristic of an image, wherein an input image is digitized to produce digital image data representative of the image and a histogram of the digital image data is produced. At least a first pixel value characteristic of a variable under which the image was derived is extracted from the histogram. A plurality of non-linear correction curves relating original pixel values to corrected pixel values for different degrees of the variable are stored in a memory, and a particular one of the correction curves is selected based at least in part on the first extracted pixel value and a predetermined corrected pixel value. Corrected image data are then formed utilizing the selected correction curve by correcting each original pixel value of the image to a respective corrected pixel value based on the relationship therebetween defined by the selected correction curve, and a non-linearity corrected image is produced based on the corrected image data.

High quality film image correction and duplication method and system

To aid radiologists in the detection of lung cancer, the authors are developing a computer-aided diagnosis system that locates areas suspicious for nodules in digital chest radiographs. The system involves a difference-image approach and various feature-extraction techniques. The authors describe nonlinear filters used in the difference-image approach. A morphological open operation and a ring-shaped median filter are applied in the difference-image step for signal enhancement and signal suppression, respectively. Using 60 clinical chest radiographs, the nonlinear filtering method detected approximately 63% of actual nodules with approximately 19 false-positive results per image. The locations of the false-positive detections, however, usually did not coincide with those from the linear filtering method. Thus, by using a combination of the detections from the two methods, the false-positive rate was reduced to two to three per image at a sensitivity of 60%.

Computerized scheme for the detection of pulmonary nodules. A nonlinear filtering technique.

RATIONALE AND OBJECTIVE. To alert radiologists to possible nodule locations and subsequently to reduce the number of false-negative diagnoses, the authors are developing a computer-aided diagnostic (CAD) scheme for the detection of lung nodules in digital chest images. METHODS. A computer-vision sch

Potential Usefulness of Computerized Nodule Detection in Screening Programs for Lung Cancer

We are developing various computer-vision schemes for the detection of masses and microcalcifications in digital mammograms. However, for the effective and efficient implementation of computer-aided diagnosis (CAD), appropriate man-machine interfaces must be developed. Thus, our plan is to incorporate our schemes into a dedicated workstation for use as a 'second opinion' in a mammographic screening program. Output from the computer would be displayed as an aid, leaving the final diagnostic decision with the radiologist.

Hitoshi Yoshimura

Papers

Image feature analysis of false-positive diagnoses produced by automated detection of lung nodules.

High quality film image correction and duplication method and system

Computerized scheme for the detection of pulmonary nodules. A nonlinear filtering technique.

Potential Usefulness of Computerized Nodule Detection in Screening Programs for Lung Cancer

Development of a smart workstation for use in mammography