Topology-based radiomic features for prediction of parotid gland cancer malignancy grade in magnetic resonance images.

PURPOSE: The malignancy grades of parotid gland cancer (PGC) have been assessed for a decision of treatment policies. Therefore, we have investigated the feasibility of topology-based radiomic features for the prediction of parotid gland cancer (PGC) malignancy grade in magnetic resonance (MR) images. MATERIALS AND METHODS: Two-dimensional T1- and T2-weighted MR images of 39 patients with PGC were selected for this study. Imaging properties of PGC can be quantified using the topology, which could be useful for assessing the number of the k-dimensional holes or heterogeneity in PGC regions using invariants of the Betti numbers. Radiomic signatures were constructed from 41,472 features obtained after a harmonization using an elastic net model. PGC patients were stratified using a logistic classification into low/intermediate- and high-grade malignancy groups. The training data were increased by four times to avoid the overfitting problem using a synthetic minority oversampling technique. The proposed approach was assessed using a 4-fold cross-validation test. RESULTS: The highest accuracy of the proposed approach was 0.975 for the validation cases, whereas that of the conventional approach was 0.694. CONCLUSION: This study indicated that topology-based radiomic features could be feasible for the noninvasive prediction of the malignancy grade of PGCs.

Deep Learning-based Lung dose Prediction Using Chest X-ray Images in Non-small Cell Lung Cancer Radiotherapy.

Purpose: This study aimed to develop a deep learning model for the prediction of V20 (the volume of the lung parenchyma that received ≥20 Gy) during intensity-modulated radiation therapy using chest X-ray images. Methods: The study utilized 91 chest X-ray images of patients with lung cancer acquired routinely during the admission workup. The prescription dose for the planning target volume was 60 Gy in 30 fractions. A convolutional neural network-based regression model was developed to predict V20. To evaluate model performance, the coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) were calculated with conducting a four-fold cross-validation method. The patient characteristics of the eligible data were treatment period (2018-2022) and V20 (19.3%; 4.9%-30.7%). Results: The predictive results of the developed model for V20 were 0.16, 5.4%, and 4.5% for the R2, RMSE, and MAE, respectively. The median error was -1.8% (range, -13.0% to 9.2%). The Pearson correlation coefficient between the calculated and predicted V20 values was 0.40. As a binary classifier with V20 <20%, the model showed a sensitivity of 75.0%, specificity of 82.6%, diagnostic accuracy of 80.6%, and area under the receiver operator characteristic curve of 0.79. Conclusions: The proposed deep learning chest X-ray model can predict V20 and play an important role in the early determination of patient treatment strategies.

Recurrence prediction with local binary pattern-based dosiomics in patients with head and neck squamous cell carcinoma.

We investigated an approach for predicting recurrence after radiation therapy using local binary pattern (LBP)-based dosiomics in patients with head and neck squamous cell carcinoma (HNSCC). Recurrence/non-recurrence data were collected from 131 patients after intensity-modulated radiation therapy. The cases were divided into training (80%) and test (20%) datasets. A total of 327 dosiomics features, including cold spot volume, first-order features, and texture features, were extracted from the original dose distribution (ODD) and LBP on gross tumor volume, clinical target volume, and planning target volume. The CoxNet algorithm was employed in the training dataset for feature selection and dosiomics signature construction. Based on a dosiomics score (DS)-based Cox proportional hazard model, two recurrence prediction models (DSODD and DSLBP) were constructed using the ODD and LBP dosiomics features. These models were used to evaluate the overall adequacy of the recurrence prediction using the concordance index (CI), and the prediction performance was assessed based on the accuracy and area under the receiver operating characteristic curve (AUC). The CIs for the test dataset were 0.71 and 0.76 for DSODD and DSLBP, respectively. The accuracy and AUC for the test dataset were 0.71 and 0.76 for the DSODD model and 0.79 and 0.81 for the DSLBP model, respectively. LBP-based dosiomics models may be more accurate in predicting recurrence after radiation therapy in patients with HNSCC.

Radiomics with artificial intelligence for precision medicine in radiation therapy.

Recently, the concept of radiomics has emerged from radiation oncology. It is a novel approach for solving the issues of precision medicine and how it can be performed, based on multimodality medical images that are non-invasive, fast and low in cost. Radiomics is the comprehensive analysis of massive numbers of medical images in order to extract a large number of phenotypic features (radiomic biomarkers) reflecting cancer traits, and it explores the associations between the features and patients' prognoses in order to improve decision-making in precision medicine. Individual patients can be stratified into subtypes based on radiomic biomarkers that contain information about cancer traits that determine the patient's prognosis. Machine-learning algorithms of AI are boosting the powers of radiomics for prediction of prognoses or factors associated with treatment strategies, such as survival time, recurrence, adverse events, and subtypes. Therefore, radiomic approaches, in combination with AI, may potentially enable practical use of precision medicine in radiation therapy by predicting outcomes and toxicity for individual patients.

Potentials of radiomics for cancer diagnosis and treatment in comparison with computer-aided diagnosis.

Computer-aided diagnosis (CAD) is a field that is essentially based on pattern recognition that improves the accuracy of a diagnosis made by a physician who takes into account the computer's "opinion" derived from the quantitative analysis of radiological images. Radiomics is a field based on data science that massively and comprehensively analyzes a large number of medical images to extract a large number of phenotypic features reflecting disease traits, and explores the associations between the features and patients' prognoses for precision medicine. According to the definitions for both, you may think that radiomics is not a paraphrase of CAD, but you may also think that these definitions are "image manipulation". However, there are common and different features between the two fields. This review paper elaborates on these common and different features and introduces the potential of radiomics for cancer diagnosis and treatment by comparing it with CAD.

Feasibility of patient dose reduction based on various noise suppression filters for cone-beam computed tomography in an image-guided patient positioning system.

We investigated the feasibility of patient dose reduction based on six noise suppression filters for cone-beam computed tomography (CBCT) in an image-guided patient positioning (IGPP) system. A midpoint dose was employed as a patient dose index. First, a reference dose (RD) and low-dose (LD)-CBCT images were acquired with a reference dose and various low doses. Second, an automated rigid registration was performed for three axis translations to estimate patient setup errors between a planning CT image and the LD-CBCT images processed by six noise suppression filters (averaging filter, median filter, Gaussian filter, edge-preserving smoothing filter, bilateral filter, and adaptive partial median filter (AMF)). Third, residual errors representing the patient positioning accuracy were calculated as Euclidean distances between the setup error vectors estimated using the LD-CBCT and RD-CBCT images. Finally, the residual errors as a function of the patient dose index were estimated for LD-CBCT images processed by six noise suppression filters, and then the patient dose indices for the filtered LD-CBCT images were obtained at the same residual error as the RD-CBCT image. This approach was applied to an anthropomorphic phantom and four cancer patients. The patient dose for the LD-CBCT images was reduced to 19% of that for the RD-CBCT image for the phantom by using AMF, while keeping a same residual error of 0.47 mm as the RD-CBCT image by applying the noise suppression filters to the LD-CBCT images. The average patient dose was reduced to 31.1% for prostate cancer patients, and it was reduced to 82.5% for a lung cancer patient by applying the AMF. These preliminary results suggested that the proposed approach based on noise suppression filters could decrease the patient dose in IGPP systems.