Evaluation of the accuracy of heart dose prediction by machine learning for selecting patients not requiring deep inspiration breath­hold radiotherapy after breast cancer surgery.

Increased heart dose during postoperative radiotherapy (RT) for left-sided breast cancer (BC) can cause cardiac injury, which can decrease patient survival. The deep inspiration breath-hold technique (DIBH) is becoming increasingly common for reducing the mean heart dose (MHD) in patients with left-sided BC. However, treatment planning and DIBH for RT are laborious, time-consuming and costly for patients and RT staff. In addition, the proportion of patients with left BC with low MHD is considerably higher among Asian women, mainly due to their smaller breast volume compared with that in Western countries. The present study aimed to determine the optimal machine learning (ML) model for predicting the MHD after RT to pre-select patients with low MHD who will not require DIBH prior to RT planning. In total, 562 patients with BC who received postoperative RT were randomly divided into the trainval (n=449) and external (n=113) test datasets for ML using Python (version 3.8). Imbalanced data were corrected using synthetic minority oversampling with Gaussian noise. Specifically, right-left, tumor site, chest wall thickness, irradiation method, body mass index and separation were the six explanatory variables used for ML, with four supervised ML algorithms used. Using the optimal value of hyperparameter tuning with root mean squared error (RMSE) as an indicator for the internal test data, the model yielding the best F2 score evaluation was selected for final validation using the external test data. The predictive ability of MHD for true MHD after RT was the highest among all algorithms for the deep neural network, with a RMSE of 77.4, F2 score of 0.80 and area under the curve-receiver operating characteristic of 0.88, for a cut-off value of 300 cGy. The present study suggested that ML can be used to pre-select female Asian patients with low MHD who do not require DIBH for the postoperative RT of BC.

Mean Heart Dose Prediction Using Parameters of Single-Slice Computed Tomography and Body Mass Index: Machine Learning Approach for Radiotherapy of Left-Sided Breast Cancer of Asian Patients.

Deep inspiration breath-hold (DIBH) is an excellent technique to reduce the incidental radiation received by the heart during radiotherapy in patients with breast cancer. However, DIBH is costly and time-consuming for patients and radiotherapy staff. In Asian countries, the use of DIBH is restricted due to the limited number of patients with a high mean heart dose (MHD) and the shortage of radiotherapy personnel and equipment compared to that in the USA. This study aimed to develop, evaluate, and compare the performance of ten machine learning algorithms for predicting MHD using a patient's body mass index and single-slice CT parameters to identify patients who may not require DIBH. Machine learning models were built and tested using a dataset containing 207 patients with left-sided breast cancer who were treated with field-in-field radiotherapy with free breathing. The average MHD was 251 cGy. Stratified repeated four-fold cross-validation was used to build models using 165 training data. The models were compared internally using their average performance metrics: F2 score, AUC, recall, accuracy, Cohen's kappa, and Matthews correlation coefficient. The final performance evaluation for each model was further externally analyzed using 42 unseen test data. The performance of each model was evaluated as a binary classifier by setting the cut-off value of MHD ≥ 300 cGy. The deep neural network (DNN) achieved the highest F2 score (78.9%). Most models successfully classified all patients with high MHD as true positive. This study indicates that the ten models, especially the DNN, might have the potential to identify patients who may not require DIBH.

Evaluation of calculation processes of apparent diffusion coefficient subtraction method (ASM) imaging.

A number of restricted diffusion (RD) imaging techniques, such as diffusion kurtosis (DK) imaging and Q space imaging, have been developed and proven to be useful for the diagnosis of diseases, including cerebral gliomas and cerebrovascular infarction. In particular, apparent diffusion coefficient (ADC) subtraction method (ASM) imaging has become available recently as a novel RD imaging technique. ASM is based on the difference between the ADC values in an image pair of two ADC maps, ADC basic (ADCb) and ADC modify (ADCm), which are created from diffusion-weighted images taken using short and long effective diffusion times, respectively. The present study aimed to assess the potential of different types of ASM imaging by comparing them with DK imaging which is the gold-standard RD imaging technique. In the present basic study using both polyethylene glycol phantom and cell-containing bio-phantom, three different types of ASM images were created using different calculation processes. ASM/A is an image calculated by dividing the absolute difference between ADCb and ADCm by ADCb several times. By contrast, ASM/S is an image created by dividing the absolute difference between ADCb and ADCm by the standard deviation of ADCb several times. As for positive ASM/A image (PASM/A), the positive image, which was resultant after subtracting ADCb from ADCm, was divided by ADCb several times. A comparison was made between the types of ASM and DK images. The results showed the same tendency between ASM/A in addition to both ASM/S and PASM/A. By increasing the number of divisions by ADCb from three to five times, ASM/A images transformed from DK-mimicking to more RD-sensitive images compared with DK images. These observations suggest that ASM/A images may prove useful for future clinical applications in RD imaging protocols for the diagnosis of diseases.

Evaluation of Fast Diffusion Kurtosis Imaging Using New Software Designed for Widespread Clinical Use.

Clinical research using restricted diffusion-weighted imaging, especially diffusion kurtosis (DK) imaging, has been progressing, with reports on its effectiveness in the diagnostic imaging of cerebral infarctions, neurodegenerative diseases, and tumors, among others. However, the application of DK imaging in daily clinical practice has not spread because of the long imaging time required and the use of specific software for image creation. Herein, with the aim of promoting clinical research using DK imaging at any medical facility, we evaluated fast DK imaging using a new software program. We developed a new macro program that produces DK images using general-purpose, inexpensive software (Microsoft Excel and ImageJ), and we evaluated fast DK imaging using bio-phantoms and a healthy volunteer in clinical trials. The DK images created by the new software with diffusion-weighted images captured with short-time imaging sequences were similar to the original DK images captured with long-time imaging sequences. The DK images using three b-values, which can reduce the imaging time by 43%, were equivalent to the DK images using five b-values. The DK imaging technique developed herein might allow any medical facility to increase its daily clinical use of DK imaging and easily conduct clinical research.

Development and Evaluation of a Short-time Imaging Method for the Clinical Study of the Apparent Diffusion Coefficient Subtraction Method.

The apparent diffusion coefficient subtraction method (ASM) was developed as a new restricted diffusionweighted imaging technique for magnetic resonance imaging (MRI). The usefulness of the ASM has been established by in vitro basic research using a bio-phantom, and clinical research on the application of the ASM for the human body is needed. Herein, we developed a short-time sequence for ASM imaging of the heads of healthy volunteers (n=2), and we investigated the similarity between the obtained ASM images and diffusion kurtosis (DK) images to determine the utility of the ASM for clinical uses. This study appears to be the first to report ASM images of the human head. We observed that the short-time sequence for the ASM imaging of the head can be scanned in approx. 3 min at 1.5T MRI. The noise reduction effect of median filter processing was confirmed on the ASM images scanned by this sequence. The obtained ASM images showed a weak correlation with the DK images, indicating that the ASM images are restricted diffusion-weighted images. The new shorttime imaging sequence could thus be used in clinical studies applying the ASM.

New field-in-field with two reference points method for whole breast radiotherapy: Dosimetric analysis and radiation-induced skin toxicities assessment.

The usefulness of the field-in-field with two reference points (FIF w/ 2RP) method, in which the dose reference points are set simultaneously at two positions in the irradiation field and the high-dose range is completely eliminated, was examined in the present study with the aim of decreasing acute skin toxicity in adjuvant breast radiotherapy (RT). A total of 573 patients with breast cancer who underwent postoperative whole breast RT were classified into 178 cases with wedge (W) method, 142 cases with field-in-field without 2 reference points (FIF w/o 2RP) method and 253 cases with FIF w/ 2RP method. Using the FIF w/ 2RP method, the high-dose range was the lowest among the three irradiation methods. The planning target volume (PTV) V105% and the breast PTV for evaluation (BPe) V105% decreased to 0.09 and 0.10%, respectively. The FIF w/ 2RP method vs. the FIF w/o 2RP method had a strong association (η) with PTV V105% (η=0.79; P<0.001) and BPe V105% (η=0.76; P<0.001). The FIF w/ 2RP method had a significant impact on lowering the skin toxicity grade in weeks 3 and 4, and increasing the occurrence of skin toxicity grade 0. The FIF w/ 2RP method vs. the W method had a moderate association with skin toxicity grade at week 3 (η=0.49; P<0.001). Using the FIF w/ 2RP method, the high-dose range V105% of the target decreased to 0%, and skin adverse events were decreased in conjunction. For patients with early-stage breast cancer, particularly patients with relatively small-sized breasts, the FIF w/ 2RP method may be an optimal irradiation method.

Investigation into the Effect of Breast Volume on Irradiation Dose Distribution in Asian Women with Breast Cancer.

Reports on irradiation dose distribution in breast cancer radiotherapy with sufficient sample size are limited in Asian patients. Elucidating dose distribution in Asian patients is particularly important as their breast volume differs compared to patients in Europe and North America. Here, we examined dose distribution in the irradiation field relative to breast volume for three irradiation methods historically used in our facility. We investigated the influence of breast volume on each irradiation method for Asian women. A total of 573 women with early-stage breast cancer were treated with breast-conserving surgery and adjuvant radiotherapy. Three methods were compared: wedge (W), field-in-field (FIF), and wedge-field-in-field (W-FIF). In patients with small breast volume, FIF decreased low- and high-dose areas within the planning target volume, and increased optimal dose area more than W. In patients with medium and large breast volumes, FIF decreased high-dose area more than W. The absolute values of correlation coefficients of breast volume to low-, optimal-, and high-dose areas and mean dose were significantly lower in FIF than in W. The correlation coefficients of V107% were 0.00 and 0.28 for FIF and W, respectively. FIF is an excellent irradiation method that is less affected by breast volume than W in Asian breast cancer patients.

Evaluation of the Imaging Process for a Novel Subtraction Method Using Apparent Diffusion Coefficient Values.

Diffusion-weighted imaging may be used to obtain the apparent diffusion coefficient (ADC), which aids the diagnosis of cerebral infarction and tumors. An ADC reflects elements of free diffusion. Diffusion kurtosis imaging (DKI) has attracted attention as a restricted diffusion imaging technique. The ADC subtraction method (ASM) was developed to visualize restricted diffusion with high resolution by using two ADC maps taken with different diffusion times. We conducted the present study to provide a bridge between the reported basic ASM research and clinical research. We developed new imaging software for clinical use and evaluated its performance herein. This software performs the imaging process automatically and continuously at the pixel level, using ImageJ software. The new software uses a macro or a plugin which is compatible with various operating systems via a Java Virtual Machine. We tested the new imaging software's performance by using a Jurkat cell bio-phantom, and the statistical evaluation of the performance clarified that the ASM values of 99.98% of the pixels in the bio-phantom and physiological saline were calculated accurately (p<0.001). The new software may serve as a useful tool for future clinical applications and restricted diffusion imaging research.

Development of a novel phantom using polyethylene glycol for the visualization of restricted diffusion in diffusion kurtosis imaging and apparent diffusion coefficient subtraction method.

The present study aimed to investigate whether polyethylene glycol (PEG) phantoms have the potential to be used as standard phantoms for magnetic resonance imaging (MRI) in order to visualize restricted diffusion in diffusion kurtosis imaging (DKI), the ADC subtraction method (ASM) and the apparent diffusion coefficient (ADC). Diffusion-weighted images of 0-120 mM PEG phantoms were captured to create ADC, DKI and ASM images with post-processing. ASM is a recently developed method for restricted diffusion imaging using the readout segmentation of long variable echo-train sequences. As the PEG concentration increases, the ADC value decreases. Conversely, an increase in DKI and ASM values is associated with increasing PEG concentration. Formulae were constructed to represent the association between PEG concentrations and ADC, DKI and ASM values. These formulae can be used to determine the required PEG concentrations to mimic arbitrary ADC, DKI and ASM values of certain diseases, including tumors and infarctions. Validation experiments were conducted using bio-phantoms and clarified that the PEG phantoms cover the range of ADC and DKI values reported in previous clinical research using 3T MRI. PEG phantoms may be useful for future MRI research involving restricted diffusion.