Gigin Lin

Uterine fibroid-like tumors: spectrum of MR imaging findings and their differential diagnosis

Uterine leiomyoma, also known as uterine fibroid, is the most common gynecological tumor, affecting almost 80% of women at some point during their lives. In the same time, other fibroid-like tumors have similar clinical presentations and about 0.5% of resected tumors of which were presumed benign fibroids in the preoperative diagnosis revealed as malignant sarcomas in the final histopathological examination. Amid the emergence of nonsurgical or minimally invasive procedures for symptomatic benign uterine fibroids, such as uterine artery embolization, high-intensity-focused ultrasound, or laparoscopic myomectomy, the preoperative diagnosis of uterine tumors through imaging becomes all the more relevant. Preoperative tissue sampling is challenging because of the variable location of the myometrial mass; thus, the preoperative evaluation of size and location is increasingly performed through magnetic resonance imaging. Features in images might also be useful for examining the full spectrum of such growths, from benign fibroids to neoplasms of uncertain behavior and malignant sarcomas. Benign fibroids include usual-type leiomyomas, myomas with degeneration, and mitotically active leiomyomas. Neoplasms of uncertain behavior include smooth muscle tumors of uncertain malignant potential, leiomyomas with bizarre nuclei, and cellular leiomyomas. Malignant sarcomas comprise leiomyosarcomas, endometrial stromal sarcomas, adenosarcomas, and carcinosarcomas. The purpose of this article is to review the spectrum of MRI findings of uterine fibroid-like tumors, from benign variants, uncertain behavior to malignant sarcomas, and update the advanced imaging modalities, including diffusion-weighted imaging, positron emission tomography/computed tomography, combining texture analysis and radiomics, to tackle this important issue.

MRI-based Ovarian Lesion Classification via a Foundation Segmentation Model and Multimodal Analysis: A Multicenter Study

Combining the Segment Anything Model with a deep learning classifier produced an efficient pipeline for classifying MRI ovarian lesions, improving segmentation speed and matching radiologists’ classification performance.

Hyperpolarized [1-13C]-pyruvate MRS evaluates immune potential and predicts response to radiotherapy in cervical cancer

Abstract Background Monitoring pyruvate metabolism in the spleen is important for assessing immune activity and achieving successful radiotherapy for cervical cancer due to the significance of the abscopal effect. We aimed to explore the feasibility of utilizing hyperpolarized (HP) [1-13C]-pyruvate magnetic resonance imaging (MRI) and magnetic resonance spectroscopy (MRS) to evaluate pyruvate metabolism in the human spleen, with the aim of identifying potential candidates for radiotherapy in cervical cancer. Methods This prospective study recruited six female patients with cervical cancer (median age 55 years; range 39–60) evaluated using HP [1-13C]-pyruvate MRI/MRS at baseline and 2 weeks after radiotherapy. Proton (1H) diffusion-weighted MRI was performed in parallel to estimate splenic cellularity. The primary outcome was defined as tumor response to radiotherapy. The Student t-test was used for comparing 13C data between the groups. Results The splenic HP [1-13C]-lactate-to-total carbon (tC) ratio was 5.6-fold lower in the responders than in the non-responders at baseline (p = 0.009). The splenic [1-13C]-lactate-to-tC ratio revealed a 1.7-fold increase (p = 0.415) and the splenic [1-13C]-alanine-to-tC ratio revealed a 1.8-fold increase after radiotherapy (p = 0.482). The blood leukocyte differential count revealed an increased proportion of neutrophils two weeks following treatment, indicating enhanced immune activity (p = 0.013). The splenic apparent diffusion coefficient values between the groups were not significantly different. Conclusions This exploratory study revealed the feasibility of HP [1-13C]-pyruvate MRS of the spleen for evaluating baseline immune potential, which was associated with clinical outcomes of cervical cancer after radiotherapy. Trial registration ClinicalTrials.gov NCT04951921, registered 7 July 2021. Relevance statement This prospective study revealed the feasibility of using HP 13C MRI/MRS for assessing pyruvate metabolism of the spleen to evaluate the patients’ immune potential that is associated with radiotherapeutic clinical outcomes in cervical cancer. Key points • Effective radiotherapy induces abscopal effect via altering immune metabolism. • Hyperpolarized 13C MRS evaluates patients’ immune potential non-invasively. • Pyruvate-to-lactate conversion in the spleen is elevated following radiotherapy. Graphical Abstract

Deep learning for fully automated tumor segmentation and extraction of magnetic resonance radiomics features in cervical cancer

To develop and evaluate the performance of U-Net for fully automated localization and segmentation of cervical tumors in magnetic resonance (MR) images and the robustness of extracting apparent diffusion coefficient (ADC) radiomics features. This retrospective study involved analysis of MR images from 169 patients with cervical cancer stage IB-IVA captured; among them, diffusion-weighted (DW) images from 144 patients were used for training, and another 25 patients were recruited for testing. A U-Net convolutional network was developed to perform automated tumor segmentation. The manually delineated tumor region was used as the ground truth for comparison. Segmentation performance was assessed for various combinations of input sources for training. ADC radiomics were extracted and assessed using Pearson correlation. The reproducibility of the training was also assessed. Combining b0, b1000, and ADC images as a triple-channel input exhibited the highest learning efficacy in the training phase and had the highest accuracy in the testing dataset, with a dice coefficient of 0.82, sensitivity 0.89, and a positive predicted value 0.92. The first-order ADC radiomics parameters were significantly correlated between the manually contoured and fully automated segmentation methods (p < 0.05). Reproducibility between the first and second training iterations was high for the first-order radiomics parameters (intraclass correlation coefficient = 0.70-0.99). U-Net-based deep learning can perform accurate localization and segmentation of cervical cancer in DW MR images. First-order radiomics features extracted from whole tumor volume demonstrate the potential robustness for longitudinal monitoring of tumor responses in broad clinical settings. U-Net-based deep learning can perform accurate localization and segmentation of cervical cancer in DW MR images. • U-Net-based deep learning can perform accurate fully automated localization and segmentation of cervical cancer in diffusion-weighted MR images. • Combining b0, b1000, and apparent diffusion coefficient (ADC) images exhibited the highest accuracy in fully automated localization. • First-order radiomics feature extraction from whole tumor volume was robust and could thus potentially be used for longitudinal monitoring of treatment responses.