A semi‐automatic method for peak and valley detection in free‐breathing respiratory waveforms

Abstract

The existing commercial software often inadequately determines respiratory peaks for patients in respiration correlated computed tomography. A semi-automatic method was developed for peak and valley detection in free-breathing respiratory waveforms. First the waveform is separated into breath cycles by identifying intercepts of a moving average curve with the inspiration and expiration branches of the waveform. Peaks and valleys were then defined, respectively, as the maximum and minimum between pairs of alternating inspiration and expiration intercepts. Finally, automatic corrections and manual user interventions were employed. On average for each of the 20 patients, 99% of 307 peaks and valleys were automatically detected in 2.8 s. This method was robust for bellows waveforms with large variations.

Feasibility Study for Markerless Tracking of Lung Tumors in Stereotactic Body Radiotherapy

“…Drifts were analyzed separately for each beam by calculating the moving average (window width of two breathing cycles) as suggested in the literature (12,13). The resulting curve was analyzed for a drift which occurred during delivery of each beam relative to its first value.…”

A Comparison of Soft-Tissue Implanted Markers and Bony Anatomy Alignments for Image-Guided Treatments of Head-and-Neck Cancers

“…To evaluate any potential dosimetric consequences on target coverage from using either of the two alignment techniques, a deformable image registration (DIR) algorithm developed by Lu et al (11)(12)(13) was used to calculate accumulated target structure dose-volume histograms (DVHs). Our clinical protocols dictate that daily MVCT localization scans include only the region of primary disease.…”

Irregular Breathing Classification From Multiple Patient Datasets Using Neural Networks

“…However, the decision boundary to distinguish the irregular patterns from diverse respirations is not clear yet [11], [16]. For example, some studies defined only two (characteristic and uncharacteristic [10]) or three (small, middle, and large [9]) types of irregular breathing motions based on the breathing amplitude to access the target dosimetry [9], [10].…”

“…Our purpose is to classify irregular patterns, given symptoms that fit into neither the regular pattern nor the regular compression pattern categorizations [17]. Respiratory patterns can be classified as normal or abnormal patterns [16]. The key point of the classification as normal or abnormal breathing patterns is how to extract the dominant feature from the original breathing datasets [18]- [24].…”