記述言語：英語   出版者・発行元：Laboratory Investigation  

Artificial intelligence models with biomarkers to predict treatment responses to radiation would be necessary to maximize the treatment outcomes of individual patients, especially with histopathology images routinely obtained before treatment. We hypothesized that multiscale features, such as genomic (GM), pathomic (PM), and topological (TP) features, could be associated with the radiation response. We investigated fusion models with multiscale features in histopathology images to predict response to radiation therapy for patients (responders) with non–small cell lung cancer. Ten radiosensitivity-related (radiosensitive and radioresistant) genes were deployed as GM features. PM features were extracted from histopathology images by conventional PM analyses. TP features represent the intrinsic properties of tumor cells using Betti numbers, which are mathematical invariants. We analyzed non–small cell lung cancer patients from The Cancer Genome Atlas and Clinical Proteomic Tumor Analysis Consortium who received radiotherapy and established 3 base models with GM, TP, and PM features, respectively, and 3 fusion models. The TP model showed a higher area under the receiver operating characteristic curve of 0.707 (P = .026, log-rank test in overall survival analysis) in the internal test data set and 0.720 (P = .136) in the external test data set. The results indicated that the TP models achieved better classification and prognostic prediction powers than the other base models. The inner-cell TP structure may have the ability to reveal the cell radiosensitivity-related information. Furthermore, the best fusion model with GM, TP, and PM features achieved the highest area under the receiver operating characteristic curve of 0.846 (P = .019) and 0.731 (P = .043) in predicting the treatment response and prognoses in the internal and external test data sets, respectively. This study demonstrated the predictive power of the multiscale fusion model for histopathology images, which may assist clinical physicians in the selection of responders to radiation for personalized radiation therapy and would be substantially beneficial for patients with cancer.

DOI： 10.1016/j.labinv.2025.104204

Web of Science

Scopus

PubMed

記述言語：英語   出版者・発行元：Radiological Physics and Technology  

Prediction of severe disease (SVD) in patients with coronavirus disease (COVID-19) pneumonia at an early stage could allow for more appropriate triage and improve patient prognosis. Moreover, the visualization of the topological properties of COVID-19 pneumonia could help clinical physicians describe the reasons for their decisions. We aimed to construct predictive models of SVD in patients with COVID-19 pneumonia at an early stage on computed tomography (CT) images using SVD-specific features that can be visualized on accumulated Betti number (BN) maps. BN maps (b0 and b1 maps) were generated by calculating the BNs within a shifting kernel in a manner similar to a convolution. Accumulated BN maps were constructed by summing BN maps (b0 and b1 maps) derived from a range of multiple-threshold values. Topological features were computed as intrinsic topological properties of COVID-19 pneumonia from the accumulated BN maps. Predictive models of SVD were constructed with two feature selection methods and three machine learning models using nested fivefold cross-validation. The proposed model achieved an area under the receiver-operating characteristic curve of 0.854 and a sensitivity of 0.908 in a test fold. These results suggested that topological image features could characterize COVID-19 pneumonia at an early stage as SVD.

DOI： 10.1007/s12194-025-00906-1

Web of Science

Scopus

PubMed

出版者・発行元：Applied Sciences Switzerland  

This study aimed to propose an automated prediction approach of the consolidation tumor ratios (CTRs) of part-solid tumors of patients treated with radiotherapy on treatment planning computed tomography images using deep learning segmentation (DLS) models. For training the DLS model for cancer regions, a total of 115 patients with non-small cell lung cancer (NSCLC) who underwent stereotactic body radiation therapy were selected as the training dataset, including solid, part-solid, and ground-glass opacity tumors. For testing the automated prediction approach of CTRs based on segmented tumor regions, 38 patients with part-solid tumors were selected as an internal test dataset A (IN) from a same institute as the training dataset, and 49 patients as an external test dataset (EX) from a public database. The CTRs for part-solid tumors were predicted as ratios of the maximum diameters of solid components to those of whole tumors. Pearson correlations between reference and predicted CTRs for the two test datasets were 0.953 (IN) and 0.926 (EX) for one of the DLS models (p < 0.01). Intraclass correlation coefficients between reference and predicted CTRs for the two test datasets were 0.943 (IN) and 0.904 (EX) for the same DLS models. The findings suggest that the automated prediction approach could be robust in calculating the CTRs of part-solid tumors.

DOI： 10.3390/app14083275

Web of Science

Scopus

担当区分：筆頭著者   記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Physical and Engineering Sciences in Medicine  

This study aimed to investigate the robustness of a deep learning (DL) fusion model for low training-to-test ratio (TTR) datasets in the segmentation of gross tumor volumes (GTVs) in three-dimensional planning computed tomography (CT) images for lung cancer stereotactic body radiotherapy (SBRT). A total of 192 patients with lung cancer (solid tumor, 118; part-solid tumor, 53; ground-glass opacity, 21) who underwent SBRT were included in this study. Regions of interest in the GTVs were cropped based on GTV centroids from planning CT images. Three DL models, 3D U-Net, V-Net, and dense V-Net, were trained to segment the GTV regions. Nine fusion models were constructed with logical AND, logical OR, and voting of the two or three outputs of the three DL models. TTR was defined as the ratio of the number of cases in a training dataset to that in a test dataset. The Dice similarity coefficients (DSCs) and Hausdorff distance (HD) of the 12 models were assessed with TTRs of 1.00 (training data: validation data: test data = 40:20:40), 0.791 (35:20:45), 0.531 (31:10:59), 0.291 (20:10:70), and 0.116 (10:5:85). The voting fusion model achieved the highest DSCs of 0.829 to 0.798 for all TTRs among the 12 models, whereas the other models showed DSCs of 0.818 to 0.804 for a TTR of 1.00 and 0.788 to 0.742 for a TTR of 0.116, and an HD of 5.40 ± 3.00 to 6.07 ± 3.26 mm better than any single DL models. The findings suggest that the proposed voting fusion model is a robust approach for low TTR datasets in segmenting GTVs in planning CT images of lung cancer SBRT.

DOI： 10.1007/s13246-023-01295-8

Web of Science

Scopus

PubMed

記述言語：英語   出版者・発行元：Cancers  

This study aimed to elucidate a computed tomography (CT) image-based biopsy with a radiogenomic signature to predict homeodomain-only protein homeobox (HOPX) gene expression status and prognosis in patients with non-small cell lung cancer (NSCLC). Patients were labeled as HOPX-negative or positive based on HOPX expression and were separated into training (n = 92) and testing (n = 24) datasets. In correlation analysis between genes and image features extracted by Pyradiomics for 116 patients, eight significant features associated with HOPX expression were selected as radiogenomic signature candidates from the 1218 image features. The final signature was constructed from eight candidates using the least absolute shrinkage and selection operator. An imaging biopsy model with radiogenomic signature was built by a stacking ensemble learning model to predict HOPX expression status and prognosis. The model exhibited predictive power for HOPX expression with an area under the receiver operating characteristic curve of 0.873 and prognostic power in Kaplan–Meier curves (p = 0.0066) in the test dataset. This study’s findings implied that the CT image-based biopsy with a radiogenomic signature could aid physicians in predicting HOPX expression status and prognosis in NSCLC.

DOI： 10.3390/cancers15082220

Web of Science

Scopus

PubMed

記述言語：英語  

記述言語：英語  

記述言語：英語  

記述言語：英語