Applying artificial intelligence using routine clinical data for preoperative diagnosis and prognosis evaluation of gastric cancer.

The present study employed artificial intelligence (AI) machine learning technology to evaluate the prognosis of gastric cancer using blood collection data, commonly used in clinical practice and subsequently performed a stratification distinct from conventional tumor-node-metastasis (TNM) classification. Experiments were conducted using four machine learning methods, namely, logistic regression (LR), random forest (RF), gradient boosting (GB) and deep neural network (DNN), to classify good or poor post-5-year prognosis based on clinicopathological data and post-5-year relapse occurrence. For each machine learning method, the importance was sorted in descending order (from the most to the least); the top features were used for clustering using the k-medoids method. The prediction accuracy and area under the curve (AUC) for 5-year survival were as follows: LR, 76.8% and 0.702; RF, 72.5% and 0.721; GB, 75.3% and 0.73; DNN, 76.9% and 0.682, respectively. The prediction accuracy and AUC for 5-year recurrence-free survival were as follows: LR, 85.5% and 0.692; RF, 79.0% and 0.721; GB, 80.5% and 0.718; DNN, 83.2% and 0.670. Clustering patients into three groups resulted in a stratification distinct from the TNM classification. In conclusion, AI machine learning using routine clinical data can help evaluate the prognosis of gastric cancer, with prognosis differing according to AI-identified clusters.

Deep learning-based coronary computed tomography analysis to predict functionally significant coronary artery stenosis.

Fractional flow reserve derived from coronary CT (FFR-CT) is a noninvasive physiological technique that has shown a good correlation with invasive FFR. However, the use of FFR-CT is restricted by strict application standards, and the diagnostic accuracy of FFR-CT analysis may potentially be decreased by severely calcified coronary arteries because of blooming and beam hardening artifacts. The aim of this study was to evaluate the utility of deep learning (DL)-based coronary computed tomography (CT) data analysis in predicting invasive fractional flow reserve (FFR), especially in cases with severely calcified coronary arteries. We analyzed 184 consecutive cases (241 coronary arteries) which underwent coronary CT and invasive coronary angiography, including invasive FFR, within a three-month period. Mean coronary artery calcium scores were 963 ± 1226. We evaluated and compared the vessel-based diagnostic accuracy of our proposed DL model and a visual assessment to evaluate functionally significant coronary artery stenosis (invasive FFR < 0.80). A deep neural network was trained with consecutive short axial images of coronary arteries on coronary CT. Ninety-one coronary arteries of 89 cases (48%) had FFR-positive functionally significant stenosis. On receiver operating characteristics (ROC) analysis to predict FFR-positive stenosis using the trained DL model, average area under the curve (AUC) of the ROC curve was 0.756, which was superior to the AUC of visual assessment of significant (≥ 70%) coronary artery stenosis on CT (0.574, P = 0.011). The sensitivity, specificity, positive and negative predictive value (PPV and NPV), and accuracy of the DL model and visual assessment for detecting FFR-positive stenosis were 82 and 36%, 68 and 78%, 59 and 48%, 87 and 69%, and 73 and 63%, respectively. Sensitivity and NPV for the prediction of FFR-positive stenosis were significantly higher with our DL model than visual assessment (P = 0.0004, and P = 0.024). DL-based coronary CT data analysis has a higher diagnostic accuracy for functionally significant coronary artery stenosis than visual assessment.

Real-time deep neural network-based automatic bowel gas segmentation on X-ray images for particle beam treatment.

Since particle beam distribution is vulnerable to change in bowel gas because of its low density, we developed a deep neural network (DNN) for bowel gas segmentation on X-ray images. We used 6688 image datasets from 209 cases as training data, 736 image datasets from 23 cases as validation data and 102 image datasets from 51 cases as test data (total 283 cases). For the training data, we prepared three types of digitally reconstructed radiographic (DRR) images (all-density, bone and gas) by projecting the treatment planning CT image data. However, the real X-ray images acquired in the treatment room showed low contrast that interfered with manual delineation of bowel gas. Therefore, we used synthetic X-ray images converted from DRR images in addition to real X-ray images.We evaluated DNN segmentation accuracy for the synthetic X-ray images using Intersection over Union, recall, precision, and the Dice coefficient, which measured 0.708 ± 0.208, 0.832 ± 0.170, 0.799 ± 0.191, and 0.807 ± 0.178, respectively. The evaluation metrics for the real X-images were less accurate than those for the synthetic X-ray images (0.408 ± 0237, 0.685 ± 0.326, 0.490 ± 0272, and 0.534 ± 0.271, respectively). Computation time was 29.7 ± 1.3 ms/image. Our DNN appears useful in increasing treatment accuracy in particle beam therapy.

Spatiotemporal forecasting of vertical track alignment with exogenous factors.

To ensure the safety of railroad operations, it is important to monitor and forecast track geometry irregularities. A higher safety requires forecasting with higher spatiotemporal frequencies, which in turn requires capturing spatial correlations. Additionally, track geometry irregularities are influenced by multiple exogenous factors. In this study, a method is proposed to forecast one type of track geometry irregularity, vertical alignment, by incorporating spatial and exogenous factor calculations. The proposed method embeds exogenous factors and captures spatiotemporal correlations using a convolutional long short-term memory. The proposed method is also experimentally compared with other methods in terms of the forecasting performance. Additionally, an ablation study on exogenous factors is conducted to examine their individual contributions to the forecasting performance. The results reveal that spatial calculations and maintenance record data improve the forecasting of vertical alignment.

Transcriptomic analysis reveals high ITGB1 expression as a predictor for poor prognosis of pancreatic cancer.

Transcriptomic analysis of cancer samples helps identify the mechanism and molecular markers of cancer. However, transcriptomic analyses of pancreatic cancer from the Japanese population are lacking. Hence, in this study, we performed RNA sequencing of fresh and frozen pancreatic cancer tissues from 12 Japanese patients to identify genes critical for the clinical pathology of pancreatic cancer among the Japanese population. Additionally, we performed immunostaining of 107 pancreatic cancer samples to verify the results of RNA sequencing. Bioinformatics analysis of RNA sequencing data identified ITGB1 (Integrin beta 1) as an important gene for pancreatic cancer metastasis, progression, and prognosis. ITGB1 expression was verified using immunostaining. The results of RNA sequencing and immunostaining showed a significant correlation (r = 0.552, p = 0.118) in ITGB1 expression. Moreover, the ITGB1 high-expression group was associated with a significantly worse prognosis (p = 0.035) and recurrence rate (p = 0.028). We believe that ITGB1 may be used as a drug target for pancreatic cancer in the future.

Machine learning with imaging features to predict the expression of ITGAV, which is a poor prognostic factor derived from transcriptome analysis in pancreatic cancer.

Radiogenomics has attracted attention for predicting the molecular biological characteristics of tumors from clinical images, which are originally a collection of numerical values, such as computed tomography (CT) scans. A prediction model using genetic information is constructed using thousands of image features extracted and calculated from these numerical values. In the present study, RNA sequencing of pancreatic ductal adenocarcinoma (PDAC) tissues from 12 patients was performed to identify genes useful in evaluating clinical pathology, and 107 PDAC samples were immunostained to verify the obtained findings. In addition, radiogenomics analysis of gene expression was performed by machine learning using CT images and constructed prediction models. Bioinformatics analysis of RNA sequencing data identified integrin αV (ITGAV) as being important for clinicopathological factors, such as metastasis and prognosis, and the results of sequencing and immunostaining demonstrated a significant correlation (r=0.625, P=0.039). Notably, the ITGAV high­expression group was associated with a significantly worse prognosis (P=0.005) and recurrence rate (P=0.003) compared with the low­expression group. The ITGAV prediction model showed some detectability (AUC=0.697), and the predicted ITGAV high­expression group was also associated with a worse prognosis (P=0.048). In conclusion, radiogenomics predicted the expression of ITGAV in pancreatic cancer, as well as the prognosis.

Prediction of the differences in tumor mutation burden between primary and metastatic lesions by radiogenomics.

Tumor mutational burden (TMB) is gaining attention as a biomarker for responses to immune checkpoint inhibitors in cancer patients. In this study, we evaluated the status of TMB in primary and liver metastatic lesions in patients with colorectal cancer (CRC). In addition, the status of TMB in primary and liver metastatic lesions was inferred by radiogenomics on the basis of computed tomography (CT) images. The study population included 24 CRC patients with liver metastases. DNA was extracted from primary and liver metastatic lesions obtained from the patients and TMB values were evaluated by next-generation sequencing. The TMB value was considered high when it equaled to or exceeded 10/100 Mb. Radiogenomic analysis of TMB was performed by machine learning using CT images and the construction of prediction models. In 7 out of 24 patients (29.2%), the TMB status differed between the primary and liver metastatic lesions. Radiogenomic analysis was performed to predict whether TMB status was high or low. The maximum values for the area under the receiver operating characteristic curve were 0.732 and 0.812 for primary CRC and CRC with liver metastasis, respectively. The sensitivity, specificity, and accuracy of the constructed models for TMB status discordance were 0.857, 0.600, and 0.682, respectively. Our results suggested that accurate inference of the TMB status is possible using radiogenomics. Therefore, radiogenomics could facilitate the diagnosis, treatment, and prognosis of patients with CRC in the clinical setting.

Deep learning-based gene selection in comprehensive gene analysis in pancreatic cancer.

The selection of genes that are important for obtaining gene expression data is challenging. Here, we developed a deep learning-based feature selection method suitable for gene selection. Our novel deep learning model includes an additional feature-selection layer. After model training, the units in this layer with high weights correspond to the genes that worked effectively in the processing of the networks. Cancer tissue samples and adjacent normal pancreatic tissue samples were collected from 13 patients with pancreatic ductal adenocarcinoma during surgery and subsequently frozen. After processing, gene expression data were extracted from the specimens using RNA sequencing. Task 1 for the model training was to discriminate between cancerous and normal pancreatic tissue in six patients. Task 2 was to discriminate between patients with pancreatic cancer (n = 13) who survived for more than one year after surgery. The most frequently selected genes were ACACB, ADAMTS6, NCAM1, and CADPS in Task 1, and CD1D, PLA2G16, DACH1, and SOWAHA in Task 2. According to The Cancer Genome Atlas dataset, these genes are all prognostic factors for pancreatic cancer. Thus, the feasibility of using our deep learning-based method for the selection of genes associated with pancreatic cancer development and prognosis was confirmed.

Development of attenuation correction methods using deep learning in brain-perfusion single-photon emission computed tomography.

PURPOSE: Computed tomography (CT)-based attenuation correction (CTAC) in single-photon emission computed tomography (SPECT) is highly accurate, but it requires hybrid SPECT/CT instruments and additional radiation exposure. To obtain attenuation correction (AC) without the need for additional CT images, a deep learning method was used to generate pseudo-CT images has previously been reported, but it is limited because of cross-modality transformation, resulting in misalignment and modality-specific artifacts. This study aimed to develop a deep learning-based approach using non-attenuation-corrected (NAC) images and CTAC-based images for training to yield AC images in brain-perfusion SPECT. This study also investigated whether the proposed approach is superior to conventional Chang's AC (ChangAC). METHODS: In total, 236 patients who underwent brain-perfusion SPECT were randomly divided into two groups: the training group (189 patients; 80%) and the test group (47 patients; 20%). Two models were constructed using Autoencoder (AutoencoderAC) and U-Net (U-NetAC), respectively. ChangAC, AutoencoderAC, and U-NetAC approaches were compared with CTAC using qualitative analysis (visual evaluation) and quantitative analysis (normalized mean squared error [NMSE] and the percentage error in each brain region). Statistical analyses were performed using the Wilcoxon signed-rank sum test and Bland-Altman analysis. RESULTS: U-NetAC had the highest visual evaluation score. The NMSE results for the U-NetAC were the lowest, followed by AutoencoderAC and ChangAC (P < 0.001). Bland-Altman analysis showed a fixed bias for ChangAC and AutoencoderAC and a proportional bias for ChangAC. ChangAC underestimated counts by 30-40% in all brain regions. AutoencoderAC and U-NetAC produced mean errors of <1% and maximum errors of 3%, respectively. CONCLUSION: New deep learning-based AC methods for AutoencoderAC and U-NetAC were developed. Their accuracy was higher than that obtained by ChangAC. U-NetAC exhibited higher qualitative and quantitative accuracy than AutoencoderAC. We generated highly accurate AC images directly from NAC images without the need for intermediate pseudo-CT images. To verify our models' generalizability, external validation is required.

Multidimensional Deep Learning Reduces False-Positives in the Automated Detection of Cerebral Aneurysms on Time-Of-Flight Magnetic Resonance Angiography: A Multi-Center Study.

Current deep learning-based cerebral aneurysm detection demonstrates high sensitivity, but produces numerous false-positives (FPs), which hampers clinical application of automated detection systems for time-of-flight magnetic resonance angiography. To reduce FPs while maintaining high sensitivity, we developed a multidimensional convolutional neural network (MD-CNN) designed to unite planar and stereoscopic information about aneurysms. This retrospective study enrolled time-of-flight magnetic resonance angiography images of cerebral aneurysms from three institutions from June 2006 to April 2019. In the internal test, 80% of the entire data set was used for model training and 20% for the test, while for the external tests, data from different pairs of the three institutions were used for training and the remaining one for testing. Images containing aneurysms > 15 mm and images without aneurysms were excluded. Three deep learning models [planar information-only (2D-CNN), stereoscopic information-only (3D-CNN), and multidimensional information (MD-CNN)] were trained to classify whether the voxels contained aneurysms, and they were evaluated on each test. The performance of each model was assessed using free-response operating characteristic curves. In total, 732 aneurysms (5.9 ± 2.5 mm) of 559 cases (327, 120, and 112 from institutes A, B, and C; 469 and 263 for 1.5T and 3.0T MRI) were included in this study. In the internal test, the highest sensitivities were 80.4, 87.4, and 82.5%, and the FPs were 6.1, 7.1, and 5.0 FPs/case at a fixed sensitivity of 80% for the 2D-CNN, 3D-CNN, and MD-CNN, respectively. In the external test, the highest sensitivities were 82.1, 86.5, and 89.1%, and 5.9, 7.4, and 4.2 FPs/cases for them, respectively. MD-CNN was a new approach to maintain sensitivity and reduce the FPs simultaneously.

Radiogenomics for predicting p53 status, PD-L1 expression, and prognosis with machine learning in pancreatic cancer.

BACKGROUND: Radiogenomics is an emerging field that integrates "Radiomics" and "Genomics". In the current study, we aimed to predict the genetic information of pancreatic tumours in a simple, inexpensive, and non-invasive manner, using cancer imaging analysis and radiogenomics. We focused on p53 mutations, which are highly implicated in pancreatic ductal adenocarcinoma (PDAC), and PD-L1, a biomarker for immune checkpoint inhibitor-based therapies. METHODS: Overall, 107 patients diagnosed with PDAC were retrospectively examined. The relationship between p53 mutations as well as PD-L1 abnormal expression and clinicopathological factors was investigated using immunohistochemistry. Imaging features (IFs) were extracted from CT scans and were used to create prediction models of p53 and PD-L1 status. RESULTS: We found that p53 and PD-L1 are significant independent prognostic factors (P = 0.008, 0.013, respectively). The area under the curve for p53 and PD-L1 predictive models was 0.795 and 0.683, respectively. Radiogenomics-predicted p53 mutations were significantly associated with poor prognosis (P = 0.015), whereas the predicted abnormal expression of PD-L1 was not significant (P = 0.096). CONCLUSIONS: Radiogenomics could predict p53 mutations and in turn the prognosis of PDAC patients. Hence, prediction of genetic information using radiogenomic analysis may aid in the development of precision medicine.

A Deep Convolutional Neural Network With Performance Comparable to Radiologists for Differentiating Between Spinal Schwannoma and Meningioma.

STUDY DESIGN: Retrospective analysis of magnetic resonance imaging (MRI). OBJECTIVE: The aim of this study was to evaluate the performance of our convolutional neural network (CNN) in differentiating between spinal schwannoma and meningioma on MRI. We compared the performance of the CNN and that of two expert radiologists. SUMMARY OF BACKGROUND DATA: Preoperative discrimination between spinal schwannomas and meningiomas is crucial because different surgical procedures are required for their treatment. A deep-learning approach based on CNNs is gaining interest in the medical imaging field. METHODS: We retrospectively reviewed data from patients with spinal schwannoma and meningioma who had undergone MRI and tumor resection. There were 50 patients with schwannoma and 34 patients with meningioma. Sagittal T2-weighted magnetic resonance imaging (T2WI) and sagittal contrast-enhanced T1-weighted magnetic resonance imaging (T1WI) were used for the CNN training and validation. The deep learning framework Tensorflow was used to construct the CNN architecture. To evaluate the performance of the CNN, we plotted the receiver-operating characteristic (ROC) curve and calculated the area under the curve (AUC). We calculated and compared the sensitivity, specificity, and accuracy of the diagnosis by the CNN and two board-certified radiologists. RESULTS: . The AUC of ROC curves of the CNN based on T2WI and contrast-enhanced T1WI were 0.876 and 0.870, respectively. The sensitivity of the CNN based on T2WI was 78%; 100% for radiologist 1; and 95% for radiologist 2. The specificity was 82%, 26%, and 42%, respectively. The accuracy was 80%, 69%, and 73%, respectively. By contrast, the sensitivity of the CNN based on contrast-enhanced T1WI was 85%; 100% for radiologist 1; and 96% for radiologist 2. The specificity was 75%, 56, and 58%, respectively. The accuracy was 81%, 82%, and 81%, respectively. CONCLUSION: We have successfully differentiated spinal schwannomas and meningiomas using the CNN with high diagnostic accuracy comparable to that of experienced radiologists. LEVEL OF EVIDENCE: 4.