European Radiology Experimental

Cer-ConvN3Unet: an end-to-end multi-parametric MRI-based pipeline for automated detection and segmentation of cervical cancer

Abstract Background We established and validated an innovative two-phase pipeline for automated detection and segmentation on multi-parametric cervical cancer magnetic resonance imaging (MRI) and investigated the clinical efficacy. Methods The retrospective multicenter study included 125 cervical cancer patients enrolled in two hospitals for 14,547 two-dimensional images. All the patients underwent pelvic MRI examinations consisting of diffusion-weighted imaging (DWI), T2-weighted imaging (T2WI), and contrast-enhanced T1-weighted imaging (CE-T1WI). The deep learning framework involved a multiparametric detection module utilizing ConvNeXt blocks and a subsequent segmentation module utilizing 3-channel DoubleU-Nets. The pipeline was trained and tested (80:20 ratio) on 3,077 DWI, 2,990 T2WI, and 8,480 CE-T1WI slices. Results In terms of reference standards from gynecologic radiologists, the first automated detection module achieved overall results of 93% accuracy (95% confidence interval 92–94%), 93% precision (92–94%), 93% recall (92–94%), 0.90 κ (0.89–0.91), and 0.93 F1-score (0.92–0.94). The second-stage segmentation exhibited Dice similarity coefficients and Jaccard values of 83% (81–85%) and 71% (69–74%) for DWI, 79% (75–82%), and 65% (61–69%) for T2WI, 74% (71–76%) and 59% (56–62%) for CE-T1WI. Conclusion Independent experiments demonstrated that the pipeline could get high recognition and segmentation accuracy without human intervention, thus effectively reducing the delineation burden for radiologists and gynecologists. Relevance statement The proposed pipeline is potentially an alternative tool in imaging reading and processing cervical cancer. Meanwhile, this can serve as the basis for subsequent work related to tumor lesions. The pipeline contributes to saving the working time of radiologists and gynecologists. Key Points An AI-assisted multiparametric MRI-based pipeline can effectively support radiologists in cervical cancer evaluation. The proposed pipeline shows high recognition and segmentation performance without manual intervention. The proposed pipeline may become a promising auxiliary tool in gynecological imaging. Graphical Abstract

Deep learning-based segmentation of multisite disease in ovarian cancer

Abstract Purpose To determine if pelvic/ovarian and omental lesions of ovarian cancer can be reliably segmented on computed tomography (CT) using fully automated deep learning-based methods. Methods A deep learning model for the two most common disease sites of high-grade serous ovarian cancer lesions (pelvis/ovaries and omentum) was developed and compared against the well-established “no-new-Net” framework and unrevised trainee radiologist segmentations. A total of 451 CT scans collected from four different institutions were used for training (n = 276), evaluation (n = 104) and testing (n = 71) of the methods. The performance was evaluated using the Dice similarity coefficient (DSC) and compared using a Wilcoxon test. Results Our model outperformed no-new-Net for the pelvic/ovarian lesions in cross-validation, on the evaluation and test set by a significant margin (p values being 4 × 10–7, 3 × 10–4, 4 × 10–2, respectively), and for the omental lesions on the evaluation set (p = 1 × 10–3). Our model did not perform significantly differently in segmenting pelvic/ovarian lesions (p = 0.371) compared to a trainee radiologist. On an independent test set, the model achieved a DSC performance of 71 ± 20 (mean ± standard deviation) for pelvic/ovarian and 61 ± 24 for omental lesions. Conclusion Automated ovarian cancer segmentation on CT scans using deep neural networks is feasible and achieves performance close to a trainee-level radiologist for pelvic/ovarian lesions. Relevance statement Automated segmentation of ovarian cancer may be used by clinicians for CT-based volumetric assessments and researchers for building complex analysis pipelines. Key points • The first automated approach for pelvic/ovarian and omental ovarian cancer lesion segmentation on CT images has been presented. • Automated segmentation of ovarian cancer lesions can be comparable with manual segmentation of trainee radiologists. • Careful hyperparameter tuning can provide models significantly outperforming strong state-of-the-art baselines. Graphical Abstract

Spectral CT in peritoneal carcinomatosis from ovarian cancer: a tool for differential diagnosis of small nodules?

AbstractThe detection of peritoneal carcinomatosis in patients with ovarian cancer is crucial to establish the correct therapeutic planning (debulking surgery versus neoadjuvant chemotherapy).Often, however, the nodules of peritoneal carcinomatosis are very small in size or have a reticular appearance that can mimic the fat stranding that is typical of acute inflammation conditions. Our hypothesis is that the use of dual-layer spectral computed tomography with its applications, such as virtual monoenergetic imaging and Z-effective imaging, might improve the detection and the characterisation of peritoneal nodules, increasing sensitivity and diagnostic accuracy, as recently described for other oncological diseases.

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

Ovarian cancer beyond imaging: integration of AI and multiomics biomarkers

AbstractHigh-grade serous ovarian cancer is the most lethal gynaecological malignancy. Detailed molecular studies have revealed marked intra-patient heterogeneity at the tumour microenvironment level, likely contributing to poor prognosis. Despite large quantities of clinical, molecular and imaging data on ovarian cancer being accumulated worldwide and the rise of high-throughput computing, data frequently remain siloed and are thus inaccessible for integrated analyses. Only a minority of studies on ovarian cancer have set out to harness artificial intelligence (AI) for the integration of multiomics data and for developing powerful algorithms that capture the characteristics of ovarian cancer at multiple scales and levels. Clinical data, serum markers, and imaging data were most frequently used, followed by genomics and transcriptomics. The current literature proves that integrative multiomics approaches outperform models based on single data types and indicates that imaging can be used for the longitudinal tracking of tumour heterogeneity in space and potentially over time. This review presents an overview of studies that integrated two or more data types to develop AI-based classifiers or prediction models.Relevance statement Integrative multiomics models for ovarian cancer outperform models using single data types for classification, prognostication, and predictive tasks.Key points• This review presents studies using multiomics and artificial intelligence in ovarian cancer.• Current literature proves that integrative multiomics outperform models using single data types.• Around 60% of studies used a combination of imaging with clinical data.• The combination of genomics and transcriptomics with imaging data was infrequently used. Graphical Abstract

The contribution of the 1H-MRS lipid signal to cervical cancer prognosis: a preliminary study

Abstract Background The aim of this study was to investigate the role of the lipid peak derived from 1H magnetic resonance (MR) spectroscopy in assessing cervical cancer prognosis, particularly in assessing response to neoadjuvant chemotherapy (NACT) of locally advanced cervical cancer (LACC). Methods We enrolled 17 patients with histologically proven cervical cancer who underwent 3-T MR imaging at baseline. In addition to conventional imaging sequences for pelvic assessment, the protocol included a single-voxel point-resolved spectroscopy (PRESS) sequence, with repetition time of 1,500 ms and echo times of 28 and 144 ms. Spectra were analysed using the LCModel fitting routine, thus extracting multiple metabolites, including lipids (Lip) and total choline (tCho). Patients with LACC were treated with NACT and reassessed by MRI at term. Based on tumour volume reduction, patients were classified as good responder (GR; tumour volume reduction > 50%) and poor responder or nonresponder (PR-or-NR; tumour volume reduction ≤ 50%). Results Of 17 patients, 11 were LACC. Of these 11, only 6 had both completed NACT and had good-quality 1H-MR spectra; 3 GR and 3 PR-or-NR. A significant difference in lipid values was observed in the two groups of patients, particularly with higher Lip values and higher Lip/tCho ratio in PR-NR patients (p =0.040). A significant difference was also observed in choline distribution (tCho), with higher values in GR patients (p = 0.040). Conclusions Assessment of lipid peak at 1H-MR spectroscopy could be an additional quantitative parameter in predicting the response to NACT in patients with LACC.