Daiki Shimokawa's scientific contributions

Developing a deep learning (DL) model for digital breast tomosynthesis (DBT) images to predict Ki-67 expression. The institutional review board approved this retrospective study and waived the requirement for informed consent from the patients. Initially, 499 patients (mean age: 50.5 years, range: 29–90 years) referred to our hospital for breast cancer were participated, 126 patients with pathologically confirmed breast cancer were selected and their Ki-67 expression measured. The Xception architecture was used in the DL model to predict Ki-67 expression levels. The high Ki-67 vs low Ki-67 expression diagnostic performance of our DL model was assessed by accuracy, sensitivity, specificity, areas under the receiver operating characteristic curve (AUC), and by using sub-datasets divided by the radiological characteristics of breast cancer. The average accuracy, sensitivity, specificity, and AUC were 0.912, 0.629, 0.985, and 0.883, respectively. The AUC of the four subgroups separated by radiological findings for the mass, calcification, distortion, and focal asymmetric density sub-datasets were 0.890, 0.750, 0.870, and 0.660, respectively. Our results suggest the potential application of our DL model to predict the expression of Ki-67 using DBT, which may be useful for preoperatively determining the treatment strategy for breast cancer.

Background: To develop a deep learning (DL) model for digital breast tomosynthesis (DBT) image to predict Ki-67 expression. Methods: The institutional review board approved this retrospective study and waived the requisite to obtain the informed consent from the patients. Initially, 499 patients (mean age of 50.5 years, ranging from 29 to 90 years) who were referred to our hospital suggestive of breast cancer were initially enrolled in this study. We selected 126 patients with pathologically confirmed breast cancer and measured Ki-67. Xception architecture was used for the DL model to predict Ki-67 expression. Diagnostic performance of the DL model was assessed by accuracy, sensitivity, specificity, and areas under the receiver operating characteristic curve (AUC). The diagnostic performance was also assessed with sub-datasets divided by radiological characteristics of breast cancer. Results: The average accuracy, sensitivity, specificity, and AUC were 0.856, 0.860, 0.654, 0.933, respectively. The AUC of the four sub-groups separated by radiological findings for the mass, calcification, distortion, and focal asymmetric density sub-dataset were 0.890, 0.750, 0.870, and 0.660, respectively. Conclusions: Our results suggest potential application of the DL model to predict the expression of Ki-67 using DBT, which may be useful in determining the treatment strategy for breast cancer preoperatively.

To develop a deep learning (DL)-based algorithm to predict the presence of stromal invasion in breast cancer using digital breast tomosynthesis (DBT). Our institutional review board approved this retrospective study and waived the requirement for informed consent from the patients. Initially, 499 patients (mean age 50.5 years, age range, 29-90 years) who were referred to our hospital under the suspicion of breast cancer and who underwent DBT between March 1 and August 31, 2019, were enrolled in this study. Among the 499 patients, 140 who underwent surgery after being diagnosed with breast cancer were selected for the analysis. Based on the pathological reports, the 140 patients were classified into two groups: those with non-invasive cancer (n = 20) and those with invasive cancer (n = 120). VGG16, Resnet50, DenseNet121, and Xception architectures were used as DL models to differentiate non-invasive from invasive cancer. The diagnostic performance of the DL models was assessed based on the area under the receiver operating characteristic curve (AUC). The AUC for the four models were 0.56 [95% confidence intervals (95% CI) 0.49-0.62], 0.67 (95% CI 0.62-0.74), 0.71 (95% CI 0.65-0.75), and 0.75 (95% CI 0.69-0.81), respectively. Our proposed DL model trained on DBT images is useful for predicting the presence of stromal invasion in breast cancer.

The purpose of this study was to develop a deep learning model to diagnose breast cancer by embedding a diagnostic algorithm that examines the asymmetry of bilateral breast tissue. This retrospective study was approved by the institutional review board. A total of 115 patients who underwent breast surgery and had pathologically confirmed breast cancer were enrolled in this study. Two image pairs [230 pairs of bilateral breast digital breast tomosynthesis (DBT) images with 115 malignant tumors and contralateral tissue (M/N), and 115 bilateral normal areas (N/N)] were generated from each patient enrolled in this study. The proposed deep learning model is called bilateral asymmetrical detection (BilAD), which is a modified convolutional neural network (CNN) model of Xception with two-dimensional tensors for bilateral breast images. BilAD was trained to classify the differences between pairs of M/N and N/N datasets. The results of the BilAD model were compared to those of the unilateral control CNN model (uCNN). The results of BilAD and the uCNN were as follows: accuracy, 0.84 and 0.75; sensitivity, 0.73 and 0.58; and specificity, 0.93 and 0.92, respectively. The mean area under the receiver operating characteristic curve of BilAD was significantly higher than that of the uCNN (p = 0.02): 0.90 and 0.84, respectively. The proposed deep learning model trained by embedding a diagnostic algorithm to examine the asymmetry of bilateral breast tissue improves the diagnostic accuracy for breast cancer.

Purpose: To develop a deep learning (DL)-based algorithm to predict the presence of stromal invasion of breast cancer on digital breast tomosynthesis (DBT). Materials and Methods: The institutional review board approved this retrospective study and waived the requisite to obtain the informed consent from the patients. Initially, 499 patients (mean age of 50.5 years, ranging from 29 to 90 years) who were referred to our hospital suggestive of breast cancer and performed DBT between March 1, 2019 and August 31, 2019, were enrolled in this study. Out of the 499 patients, 140 patients who were performed surgery with diagnosed breast cancer were finally selected. Based on the pathological reports, 140 patients were divided to be categorized as 20 patients with non-invasive cancer and 120 patients with invasive cancer. Xception architecture was used for the DL model to differentiate non-invasive cancer and invasive cancer. Diagnostic performance of the DL model was assessed by accuracy, sensitivity, specificity, and areas under the receiver operating characteristic curve (AUC). Results: The average accuracy, sensitivity, specificity, and AUC were 0.897, 0.909, 0.758, and 0.749, respectively. Conclusion: The proposed DL model trained on DBT images is useful to predict the presence of stromal invasion of breast cancer. Secondary abstract The proposed deep learning (DL) model trained on digital breast tomosynthesis (DBT) images is useful to predict the presence of stromal invasion of breast cancer.

A previous study reported that exponentiating pixel values of a medical can be used for DA through enhancing contrast of the image. However, it is still unclear whether exponentiating pixel values of CXR images can be used for DA with CNN. The aim of this study is to evaluate the effectiveness of exponentiating pixel values for DA using CNN in the task of classifying normal and abnormal CXR images. In constructing an image for DA, each pixel value of the original images was exponentiated by the exponent ranging from 1 to 10, incrementing by 0.5. We call this image as exponentiated image (EI). For each exponent (1.0, 1.5, 1.5, 2.0,..., 10.0), the CNN model was trained using the original training dataset and EI for 40 epochs. Test accuracy was calculated at the end of each epoch using the test dataset. The maximum test accuracy (MTA) among the 40 test accuracies was saved for statistical analysis. This process was repeated 50 times for each exponent (1.0, 1.5, 1.5, 2.0, ..., 10.0). The mean MTA for each exponent (1.5, 1.5, 2.0, ..., 10.0) was compared using Student′s t-test, to that of 1.0. The mean MTA when the exponent was 1.0 was 0.749 (reference). The mean MTA was higher than the reference at exponent values 4.5(MTA=0.762, p-value=0.014), 5.0(0.762, 0.019), 5.5(0.772, 2.9 ×10 ⁻⁵ ), and 6.5(0.763, 0.010). Exponentiating pixel values can be used for DA with CNN to classify normal and abnormal CXR images.