Breast cancer is one of the most harmful diseases for women with the highest morbidity. An efficient way to decrease its mortality is to diagnose cancer earlier by screening. Clinically, the best approach of screening for Asian women is ultrasound images combined with biopsies. However, biopsy is invasive and it gets incomprehensive information of the lesion. The aim of this study is to build a model for automatic detection, segmentation, and classification of breast lesions with ultrasound images. Based on deep learning, a technique using Mask regions with convolutional neural network was developed for lesion detection and differentiation between benign and malignant. The mean average precision was 0.75 for the detection and segmentation. The overall accuracy of benign/malignant classification was 85%. The proposed method provides a comprehensive and noninvasive way to detect and classify breast lesions.

Radiomics, which extract large amount of quantification image features from diagnostic medical images had been widely used for prognostication, treatment response prediction and cancer detection. The treatment options for lung nodules depend on their diagnosis, benign or malignant. Conventionally, lung nodule diagnosis is based on invasive biopsy. Recently, radiomics features, a non-invasive method based on clinical images, have shown high potential in lesion classification, treatment outcome prediction. Lung nodule classification using radiomics based on Computed Tomography (CT) image data was investigated and a 4-feature signature was introduced for lung nodule classification. Retrospectively, 72 patients with 75 pulmonary nodules were collected. Radiomics feature extraction was performed on non-enhanced CT images with contours which were delineated by an experienced radiation oncologist. Among the 750 image features in each case, 76 features were found to have significant differences between benign and malignant lesions. A radiomics signature was composed of the best 4 features which included Laws_LSL_min, Laws_SLL_energy, Laws_SSL_skewness and Laws_EEL_uniformity. The accuracy using the signature in benign or malignant classification was 84% with the sensitivity of 92.85% and the specificity of 72.73%. The classification signature based on radiomics features demonstrated very good accuracy and high potential in clinical application.

Currently, the inhomogeneity of the pulmonary function is not considered when treatment plans are generated in thoracic cancer radiotherapy. This study evaluates the dose of treatment plans on highly-functional volumes and performs functional treatment planning by incorporation of ventilation data from 4D-CT. Eleven patients were included in this retrospective study. Ventilation was calculated using 4D-CT. Two treatment plans were generated for each case, the first one without the incorporation of the ventilation and the second with it. The dose of the first plans was overlapped with the ventilation and analyzed. Highly-functional regions were avoided in the second treatment plans. For small targets in the first plans (PTV < 400 cc, 6 cases), all V5, V20 and the mean lung dose values for the highly-functional regions were lower than that of the total lung. For large targets, two out of five cases had higher V5 and V20 values for the highly-functional regions. All the second plans were within constraints. Radiation treatments affect functional lung more seriously in large tumor cases. With compromise of dose to other critical organs, functional treatment planning to reduce dose in highly-functional lung volumes can be achieved.

This study used radiomics image analysis to examine the differences of texture feature values extracted from oropharyngeal and hypopharyngeal cancer positron emission tomography (PET) images on various tumor segmentations, and finds the proper and stable feature groups. A total of 80 oropharyngeal and hypopharyngeal cancer cases were retrospectively recruited. Radiomics method was applied to the PET image for the 80 oropharyngeal and hypopharyngeal cancer cases to extract texture features from various defined metabolic volumes. Kruskal-Wallis one-way analysis of variance method was used to test whether feature value difference exists between groups, which were grouped by stage, response to treatment, and recurrence. If there was a significant difference, the corresponding feature cutoff value was applied to the Kaplan–Meier estimator to estimate the survival functions. For the various defined metabolic volumes, there were 16 features that had significant differences between early (T1, T2) and late tumor stages (T3, T4). Five images and 2 textural features were found to be able to predict the tumor response and recurrence, respectively, with the areas under the receiver operating characteristic curves reaching 0.7. The histogram entropy was found to be a good predictor of overall survival (OS) and primary relapse-free survival (PRFS) of oropharyngeal and hypopharyngeal cancer patients. Textural features from PET images provide predictive and prognostic information in tumor staging, tumor response, recurrence, and have the potential to be a prognosticator for OS and PRFS in oropharyngeal and hypopharyngeal cancer.

Purpose. Respiratory motion presents significant challenges for accurate PET/CT. It often introduces apparent increase of lesion size, reduction of measured standardized uptake value (SUV), and the mismatch in PET/CT fusion images. In this study, we developed the motion freeze method to use 100% of the counts collected by recombining the counts acquired from all phases of gated PET data into a single 3D PET data, with correction of respiration by deformable image registration.Methods. Six patients with diagnosis of lung cancer confirmed by oncologists were recruited. PET/CT scans were performed with Discovery STE system. The 4D PET/CT with the Varian real-time position management for respiratory motion tracking was followed by a clinical 3D PET/CT scan procedure in the static mode. Motion freeze applies the deformation matrices calculated by optical flow method to generate a single 3D effective PET image using the data from all the 4D PET phases.Results. The increase in SUV and decrease in tumor size with motion freeze for all lesions compared to the results from 3D and 4D was observed in the preliminary data of lung cancer patients. In addition, motion freeze substantially reduced tumor mismatch between the CT image and the corresponding PET images.Conclusion. Motion freeze integrating 100% of the PET counts has the potential to eliminate the influences induced by respiratory motion in PET data.