Lesion Subtlety Research Articles

Automated Registration for Dual-View X-Ray Mammography Using Convolutional Neural Networks.

Automated registration algorithms for a pair of 2D X-ray mammographic images taken from two standard imaging angles, namely, the craniocaudal (CC) and the mediolateral oblique (MLO) views, are developed. A fully convolutional neural network, a type of convolutional neural network (CNN), is employed to generate a pixel-level deformation field, which provides a mapping between masses in the two views. Novel distance-based regularization is employed, which contributes significantly to the performance. The developed techniques are tested using real 2D mammographic images, slices from real 3D mammographic images, and synthetic mammographic images. Architectural variations of the neural network are investigated and the performance is characterized from various aspects including image resolution, breast density, lesion size, lesion subtlety, and lesion Breast Imaging-Reporting and Data System (BI-RADS) category. Our network outperformed the state-of-the-art CNN-based and non-CNN-based registration techniques, and showed robust performance across various tissue/lesion characteristics. The proposed methods provide a useful automated tool for co-locating lesions between the CC and MLO views even in challenging cases. Our methods can aid clinicians to establish lesion correspondence quickly and accurately in the dual-view X-ray mammography, improving diagnostic capability.

Endoscopic Mucosal Imaging of Gastrointestinal Neoplasia in 2013

The holy grail of gastrointestinal endoscopy consists of the detection, in vivo characterization, and endoscopic removal of early or premalignant mucosal lesions. While our ability to achieve this goal has improved substantially since the development of the modern video-endoscope, inadequate visual inspection, errors of interpretation, and lesion subtlety all contribute to the continued suboptimal detection and assessment of early neoplasia. A myriad of new technologies has thus emerged that may help resolve these shortcomings; high magnification endoscopes, as well as the techniques of dye-based and virtual chromoendoscopy, are now widely available, while confocal laser endomicroscopy and endocystoscopy, optical coherence tomography, and autofluorescence imaging are generally applicable only in a research setting. Such technologies can be broadly categorized according to whether they potentially afford endoscopists improved detection, or real-time characterization, of mucosal lesions. Enhanced detection of otherwise "invisible" lesions, such as a flat area of intramucosal adenocarcinoma within Barrett's esophagus, carries the potential of an endoscopic cure prior to the development into a more advanced or metastatic disease. The ability to characterize a lesion to achieve an in vivo diagnosis, such as a colonic polyp, potentially affords endoscopists the ability to decide which lesions require removal and which can be safely left behind or discarded without histological assessment. Furthermore targeted biopsies, such as in the surveillance of chronic colitis, may prove to be more accurate and efficacious than the current protocol of random biopsies. An important caveat in the discussion of developing technologies in early cancer detection is the fundamental importance of a health-care system that promotes screening programs to recruit at-risk individuals. The ideal tool to optimize the use of endoscopy in population screening would be a panel of reliable biomarkers (blood, stool, or urine) that could effectively select a high-risk group, thus reducing the indiscriminate use of an expensive technology. The following review summarizes the current endoscopic imaging techniques available, and in development, for the early identification of gastrointestinal neoplasia.

Use of a Computer-aided Detection System to Detect Missed Lung Cancer at Chest Radiography

To study the ability of a computer-aided detection (CAD) system to detect lung cancer overlooked at initial interpretation by the radiologist. Institutional review board approval was given for this study. Patient consent was not required; a HIPAA waiver was granted because of the retrospective nature of the data collection. In patients with lung cancer diagnosed from 1995 to 2006 at two institutions, each chest radiograph obtained prior to tumor discovery was evaluated by two radiologists for an overlooked lesion. The size and location of the nodules were documented and graded for subtlety (grades 1-4, 1 = very subtle). Each radiograph with a missed lesion was analyzed by a commercial CAD system, as was the follow-up image at diagnosis. An age- and sex-matched control group was used to assess CAD false-positive rates. Missed lung cancer was found in 89 patients (age range, 51-86 years; mean age, 65 years; 80 men, nine women) on 114 radiographs. Lesion size ranged from 0.4 to 5.5 cm (mean, 1.8 cm). Lesions were most commonly peripheral (n = 63, 71%) and in upper lobes (n = 67, 75%). Lesion subtlety score was 1, 2, 3, or 4 on 43, 49, 17, and five radiographs, respectively. CAD identified 53 (47%) and 46 (52%) undetected lesions on a per-image and per-patient basis, respectively. The average size of lesions detected with CAD was 1.73 cm compared with 1.85 cm for lesions that were undetected (P = .47). A significant difference (P = .017) was found in the average subtlety score between detected lesions (score, 2.06) and undetected lesions (score, 1.68). An average of 3.9 false-positive results occurred per radiograph; an average of 2.4 false-positive results occurred per radiograph for the control group. CAD has the potential to detect approximately half of the lesions overlooked by human readers at chest radiography.

Visual Search of Mammographic Images: Influence of Lesion Subtlety 1

The goal of this study is to determine whether mammographic lesion subtlety influences the detection accuracy and visual search parameters of radiologists. Six radiologists searched a set of 20 mammograms with at least two lesions per image (masses and/or microcalcifications). Eye position was recorded. False-negative (FN) and true-positive (TP) decisions were correlated with lesion subtlety and visual search parameters of time to first hit, total dwell time, and number of return fixations. Lesions with lower subtlety ratings were detected later in the search than more obvious ones (FN later than TP decisions). When subtler lesions were detected (TP), dwell time was longer than for more obvious lesions, but FN decisions received shorter total dwell. Subtler lesions, when detected (TP), received more total fixation clusters than more obvious ones, but FN decisions received fewer. Subtle mammographic lesions are associated with significantly different visual search parameters than obvious lesions, explaining in part why they are missed more often. Developing tools to improve lesion visibility may improve detection.