Exploring Baseline Shift Prediction in Respiration Induced Tumor Motion

Balasubramanian, Arvind; Shamsuddin, Rittika; Cheung, Yam Ki; Sawant, Amit; Prabhakaran, Balakrishnan

doi:10.1109/ichi.2014.28

Cited by 4 publications

(6 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Physicians may develop customized motion-management and treatment plans to address each such patient profile. In a previous study [12], on predicting anomalous respiratory motion pattern, we observed that when the tumor motion characteristics obtained from one patient are used to train a model to predict the motion pattern for a different patient, the prediction accuracy declines significantly. On the other hand, if some tumor motion samples from the patient to be tested are made available to the online learner, its performance shows a considerable improvement.…”

Section: Introductionmentioning

confidence: 87%

“…For our previous study [12], we identified five general behavior displayed by the fractions: steady state, increasing state, decreasing state, increasing baseline and decreasing baseline. So, we set q to be (3,5,7).…”

Section: Step 2: Clusteringmentioning

confidence: 99%

“…The tumor motion is detected by steroscopic X-ray imaging and estimated by the correlation of external and internal markers used for detection. For more information and description, please refer to [12], [13], [14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Calculating Patient Similarity Based on Respiration Induced Tumor Motion

Shamsuddin

Balasubramanian

Sawant

et al. 2015

2015 International Conference on Healthcare Informatics

Self Cite

View full text Add to dashboard Cite

In stereotactic radiotherapy for thoracic and abdominal tumors, respiratory motion management is crucial for improving efficacy of treatment, while minimizing risk to heathy tissue and organs. Since tumor motion exhibits dynamic variation in characteristics, analyzing the behavior distribution of tumor motion can improve treatment planning. Identifying similarities among patients is an intuitive step towards patient profiling for optimal treatment strategy. This paper investigates how patients, undergoing radiotherapy, can be clustered into five treatment groups, which are identified by medical physicists. And in order to do so, we propose a combination of an adaptive segmentation technique and couple it with a setwise clustering approach for measuring similarity between patients. Our methods aim to group the patients solely based on their tumor motion traces brought about by respiration. Through a series of empirical and statistical analyses, we explore the impact of different feature sets and processing methodologies on the proposed patient grouping approach.

show abstract

Section: Introductionmentioning

confidence: 87%

Section: Step 2: Clusteringmentioning

confidence: 99%

See 1 more Smart Citation

Calculating Patient Similarity Based on Respiration Induced Tumor Motion

Shamsuddin

Balasubramanian

Sawant

et al. 2015

2015 International Conference on Healthcare Informatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…If the dataset was annotated, then even in the absence of control dataset, we could have reduced our result to a single accuracy value. Our previous works, [3], [16] and [4], are centered around this dataset. Even though [3] and [16] use very similar approaches as used in this paper, due to difference in target application, we cannot provide a comparison.…”

Section: A Note On Methods Performancementioning

confidence: 99%

Developing a low dimensional patient class profile in accordance to their respiration-induced tumor motion

2017

Self Cite

View full text Add to dashboard Cite

Tumor location displacement caused by respiration-induced motion reduces the efficacy of radiation therapy. Three medically relevant patterns are often observed in the respirationinduced motion signal: baseline shift, ES-Range shift, and D-Range shift. In this paper, for patients with lower body cancer, we develop class profiles (a low dimensional pattern frequency structure) that characterize them in terms of these three medically relevant patterns. We propose an adaptive segmentation technique that turns each respiration-induced motion signal into a multi-set of segments based on persistent variations within the signal. These multi-sets of segments is then probed for base behaviors. These base behaviors are then used to develop the group/class profiles using a modified version of the clustering technique described in [1]. Finally, via quantitative analysis, we provide a medical characterization for the class profiles, which can be used to explore breathing intervention technique. We show that, with i) carefully designed feature sets, ii) the proposed adaptive segmentation technique, iii) the reasonable modifications to an existing clustering algorithm for multi-sets, and iv) the proposed medical characterization methodology, it is possible to reduce the time series respiration-induced motion signals into a compact class profile. One of our co-authors is a medical physician and we used his expert opinion to verify the results.

show abstract

“…Abstract-Both our preliminary works [1], [2], on biomedical sensor signal processing, have focused on abdominal tumor motion traces. In stereotactic radiotherapy for thoracic and abdominal tumors, respiratory motion management is crucial for improving efcacy of treatment, while minimizing risk to heathy tissue and organs.…”

mentioning

confidence: 99%

Prediction and Tracking Changes in Bio-medical Sensor Data

Shamsuddin

2015

2015 International Conference on Healthcare Informatics

Self Cite

View full text Add to dashboard Cite

Both our preliminary works [1], [2], on biomedical sensor signal processing, have focused on abdominal tumor motion traces. In stereotactic radiotherapy for thoracic and abdominal tumors, respiratory motion management is crucial for improving efcacy of treatment, while minimizing risk to heathy tissue and organs. Since tumor motion exhibits dynamic variation in characteristics, between and within patients, our first work concentrated on predicting imminent anomalous or irregular tumor motion ahead of its occurrence, and our second work consists of analysis of behavioral distribution of tumor motion, used for patient grouping with the aim to improve treatment planning.As an immediate step forward for improving treatment planning for patients with abdominal tumor, we are currently focusing on developing patient profiles. The profiles will be in the form of a histogram, based on behaviors illustrated by a patient during a particular treatment session. We expect the patient profiles to advance interpretability of patient groping or clusters, which in return will improve the decision of choosing a treatment plan. We need to decide the best distance metric to use for histogram comparison and wish to reduce the number of working parameters needed to describe the profile.

show abstract

Exploring Baseline Shift Prediction in Respiration Induced Tumor Motion

Cited by 4 publications

References 2 publications

Calculating Patient Similarity Based on Respiration Induced Tumor Motion

Calculating Patient Similarity Based on Respiration Induced Tumor Motion

Developing a low dimensional patient class profile in accordance to their respiration-induced tumor motion

Prediction and Tracking Changes in Bio-medical Sensor Data

Contact Info

Product

Resources

About