Multi-Criteria Optimization and RapidPlan for Improved Organs at Risk Sparing in Treatment Planning of Malignant Pleural Mesothelioma

PURPOSE/OBJECTIVE(S)

Treatment planning for malignant pleural mesothelioma is complex and time-consuming owing to the large volume of the target as well as its overlap and proximity to critical organs. Knowledge-based planning (KBP) model using RapidPlan (RP) was previously developed and clinically tested at our institution for treatment planning of these cases that had undergone pleurectomy-decortication, and therefore had two intact-lungs. The aim of this work is to investigate if multi-criteria optimization (MCO) can further improve the RP model with respect to organ at risk (OAR) sparing without compromising target coverage.

MATERIALS/METHODS

The RP model was trained with clinically accepted plans of 57 patients that used Volumetric Modulated Arc Therapy (VMAT) with 2 partial arcs and 6 MV photons. The dose volume histogram (DVH) estimation model was trained to estimate doses to the heart, ipsilateral lung, total lung, contralateral lung, stomach, esophagus, kidneys and liver. Clinical treatment plans for 12 patients were re-planned using RP as well as a combination of RP and MCO. Application of MCO was after RP and used tradeoff exploration to navigate to the improved dose distribution on a Pareto surface. Selection of a plan that further improved OAR sparing while maintaining coverage constraints of PTV D95 and V95 ≥ 94% was made. Dosimetric parameters for clinical plans (CP), plans using RP as well as plans generated with RP and MCO were all compared for 12 new validation cases. Wilcoxon sign-rank test was used for statistical significance testing.

RESULTS

The mean heart dose was reduced from 20.9 Gy ± 3.2 Gy for CP to 17.1 Gy ± 4.2 Gy with RP and further to 13.8 Gy ± 3.3 Gy with RP and MCO. The heart V30 Gy was reduced from 23.7% ± 8% to 18.2% ± 9.4% with RP and further to 13.6% ± 5.7% with RP and MCO. The corresponding results for contralateral lung V5 Gy were 68.6% ± 14.1% with CP, 50% ± 26.3% with RP and 45.3% ± 22.8% with RP and MCO, while the mean esophagus dose was reduced from 26.5 Gy ± 3.1 Gy to 21.5 Gy ± 4.7 Gy with RP and further to 19.1 Gy ± 4.2 Gy with RP and MCO. All these dosimetric improvements were statistically significant (p<0.001). However, improvements with RP and MCO for the total lung mean and V20 Gy, liver mean, stomach mean and kidney V18 Gy were marginal over the RP. Sparing of ipsilateral lung V20 Gy was maintained at ≥ 50 cc on average for all plans. PTV D95 and V95 were both normalized at 94%.

CONCLUSION

Combination of RP and MCO significantly improved sparing of the OARs, especially the heart, contralateral lung and esophagus without compromising coverage or doses to other structures. Since doses to the heart, and contralateral lung are known to correlate with incidence of radiation pneumonitis, it would be prudent to consider planning with both RP and MCO to help determine the optimal treatment plan for the individual patient's anatomy.

Classification of breast masses in ultrasonic B-mode images using a compounding technique in the Nakagami distribution domain

Classification of masses in ultrasonic B-mode images of the breast tissue using "normalized" parameters of the Nakagami distribution was recently investigated. The technique, however, did not yield performances that were comparable to those of an experienced radiologist, and utilized only a single image for tissue characterization. Because radiologists commonly use two to four images of a mass for characterization, a similar procedure is developed here. A simple summation of the normalized Nakagami parameters from two different images of a mass is utilized for classification as benign or malignant. The performance of the normalized Nakagami parameters before and after the summation has been carried out through a receiver operating characteristic (ROC) study. The bootstrap procedure has been utilized to compute the mean and SD of the ROC area, A(z), obtained for each parameter. It has been observed that combining normalized Nakagami parameters from two images of the mass may help to improve classification performance over that from utilizing the parameters of just a single image. The performance of this automated parameter-based approach appears to match that of a trained radiologist.

Computer aided classification of masses in ultrasonic mammography

Frequency compounding was recently investigated for computer aided classification of masses in ultrasonic B-mode images as benign or malignant. The classification was performed using the normalized parameters of the Nakagami distribution at a single region of interest at the site of the mass. A combination of normalized Nakagami parameters from two different images of a mass was undertaken to improve the performance of classification. Receiver operating characteristic (ROC) analysis showed that such an approach resulted in an area of 0.83 under the ROC curve. The aim of the work described in this paper is to see whether a feature describing the characteristic of the boundary can be extracted and combined with the Nakagami parameter to further improve the performance of classification. The combination of the features has been performed using a weighted summation. Results indicate a 10% improvement in specificity at a sensitivity of 96% after combining the information at the site and at the boundary. Moreover, the technique requires minimal clinical intervention and has a performance that reaches that of the trained radiologist. It is hence suggested that this technique may be utilized in practice to characterize breast masses.

Classification of ultrasonic B mode images of the breast using frequency diversity and Nakagami statistics

The parameters of the Nakagami distribution have been utilized in the past to classify lesions in breast tissue as benign or malignant. To avoid the effect of operatorgain settings on the parameters of the Nakagami distribution, normalized parameters were utilized for the classification. The normalized parameter was defined as the ratio of the parameter at the site of the lesion to its average value over several regions away from the site. This technique, however, was very time consuming. In this paper, the application of frequency diversity and compounding is explored to achieve this normalization. Lesions are classified using these normalized parameters at the site. A receiver operating characteristic (ROC) analysis of the parameters of the Nakagami distribution has been conducted before and after compounding on a data set of 60 benign and 65 malignant lesions. The ROC results indicate that this technique can reasonably classify lesions in breast tissue as benign or malignant.

Use of frequency diversity and Nakagami statistics in ultrasonic tissue characterization

The Nakagami distribution was recently proposed as a generalized model for the envelope of the backscattered ultrasonic echo from tissue. The parameters of the Nakagami model were also shown to be useful in tissue characterization. This paper explores the possibility of enhancing the ability of these parameters for tissue characterization through the techniques of diversity and compounding. Frequency diversity has been used to create multiple versions of the envelope, which are then combined. This compounded envelope has been modeled, and its parameters have been analyzed. The ability of these new parameters to enhance tissue characterization is studied using computer simulation and experiments on tissue-mimicking phantoms. Results indicate that the use of frequency diversity and compounding may indeed improve the ability of the parameters of the Nakagami model to separate different number densities of scatterers. Therefore, it is suggested that such an approach may lead to better techniques in ultrasonic tissue characterization.

Classification of ultrasonic B-mode images of breast masses using Nakagami distribution

The Nakagami distribution was proposed recently for modeling the echo from tissue. In vivo breast data collected from patients with lesions were studied using this Nakagami model. Chi-square tests showed that the Nakagami distribution is a better fit to the envelope than the Rayleigh distribution. Two parameters, m (effective number) and alpha (effective cross section), associated with the Nakagami distribution were used for the classification of breast masses. Data from 52 patients with breast masses/lesions were used in the studies. Receiver operating characteristics (ROC) were calculated for the classification methods based on these two parameters. The results indicate that these parameters of the Nakagami distribution may be useful in classification of the breast abnormalities. The Nakagami distribution may be a reasonable means to characterize the backscattered echo from breast tissues toward a goal of an automated scheme for separating benign and malignant breast masses.

Use of the K-distribution for classification of breast masses

The K-distribution had been introduced as a valid model to represent the statistics of the envelope of the backscattered echo from phantom and tissue. This paper investigates the efficacy of the parameters of this statistical model; namely, the effective number and the effective cross-section, to characterize breast lesions as benign or malignant. Based on the normalized values of the effective number and the effective scattering cross-section, images containing benign and malignant masses were classified for a data set from 52 patients having breast masses/lesions. The receiver operating characteristic (ROC) curves were then obtained to test the classification based on these two parameters. The results indicate that the parameters of the K-distribution may be useful in classification of the breast lesions as benign and malignant.