What’s New in Imaging for Gynecologic Cancer?

Deep-learning models for image-based gynecological cancer diagnosis: a systematic review and meta- analysis

Introduction

Gynecological cancers pose a significant threat to women worldwide, especially those in resource-limited settings. Human analysis of images remains the primary method of diagnosis, but it can be inconsistent and inaccurate. Deep learning (DL) can potentially enhance image-based diagnosis by providing objective and accurate results. This systematic review and meta-analysis aimed to summarize the recent advances of deep learning (DL) techniques for gynecological cancer diagnosis using various images and explore their future implications.

Methods

The study followed the PRISMA-2 guidelines, and the protocol was registered in PROSPERO. Five databases were searched for articles published from January 2018 to December 2022. Articles that focused on five types of gynecological cancer and used DL for diagnosis were selected. Two reviewers assessed the articles for eligibility and quality using the QUADAS-2 tool. Data was extracted from each study, and the performance of DL techniques for gynecological cancer classification was estimated by pooling and transforming sensitivity and specificity values using a random-effects model.

Results

The review included 48 studies, and the meta-analysis included 24 studies. The studies used different images and models to diagnose different gynecological cancers. The most popular models were ResNet, VGGNet, and UNet. DL algorithms showed more sensitivity but less specificity compared to machine learning (ML) methods. The AUC of the summary receiver operating characteristic plot was higher for DL algorithms than for ML methods. Of the 48 studies included, 41 were at low risk of bias.

Conclusion

This review highlights the potential of DL in improving the screening and diagnosis of gynecological cancer, particularly in resource-limited settings. However, the high heterogeneity and quality of the studies could affect the validity of the results. Further research is necessary to validate the findings of this study and to explore the potential of DL in improving gynecological cancer diagnosis.

Distribution of prostate specific membrane antigen (PSMA) on PET-MRI in patients with and without ovarian cancer

OBJECTIVES

Ovarian cancer is the most lethal cancer and future research needs to focus on the early detection and exploration of new therapeutic agents. The objectives of this proof-of-concept study are to assess the feasibility of PSMA 18F-DCFPyl PET/MR imaging for detecting ovarian cancer and to evaluate the PSMA distribution in patients with and without ovarian cancer.

METHODS

This prospective pilot proof-of-concept study in patients with and without ovarian cancers occurred between October 2017 and January 2020. Patients were recruited from gynecologic oncology or hereditary ovarian cancer clinics, and underwent surgical removal of the uterus and ovaries for gynecologic indications. PSMA 18F-DCFPyl PET/MRI was obtained prior to standard of care surgery.

RESULTS

Fourteen patients were scanned: four patients with normal ovaries, six patients with benign ovarian lesions, and four patients with malignant ovarian lesions. Tracer uptake in normal ovaries (SUVmax = 2.8 ± 0.4) was greater than blood pool (SUVmax = 1.8 ± 0.5, p < 0.0001). Tracer uptake in benign ovarian lesions (2.2 ± 1.0) did not differ significantly from blood pool (p = 0.331). Tracer uptake in ovarian cancer (SUVmax = 7.8 ± 3.8) was greater than blood pool (p < 0.0001), normal ovaries (p = 0.0014), and benign ovarian lesions (p = 0.005).

CONCLUSION

PET/MR imaging detected PSMA uptake in ovarian cancer, with little to no uptake in benign ovarian findings. These results are encouraging and further studies in a larger patient cohort would be useful to help determine the extent and heterogeneity of PSMA uptake in ovarian cancer patients.

MRI-based radiomics model for distinguishing Stage I endometrial carcinoma from endometrial polyp: a multicenter study

BACKGROUND

Patients with early endometrial carcinoma (EC) have a good prognosis, but it is difficult to distinguish from endometrial polyps (EPs).

PURPOSE

To develop and assess magnetic resonance imaging (MRI)-based radiomics models for discriminating Stage I EC from EP in a multicenter setting.

MATERIAL AND METHODS

Patients with Stage I EC (n = 202) and EP (n = 99) who underwent preoperative MRI scans were collected in three centers (seven devices). The images from devices 1-3 were utilized for training and validation, and the images from devices 4-7 were utilized for testing, leading to three models. They were evaluated by the area under the receiver operating characteristic curve (AUC) and metrics including accuracy, sensitivity, and specificity. Two radiologists evaluated the endometrial lesions and compared them with the three models.

RESULTS

The AUCs of device 1, 2_ada, device 1, 3_ada, and device 2, 3_ada for discriminating Stage I EC from EP were 0.951, 0.912, and 0.896 for the training set, 0.755, 0.928, and 1.000 for the validation set, and 0.883, 0.956, and 0.878 for the external validation set, respectively. The specificity of the three models was higher, but the accuracy and sensitivity were lower than those of radiologists.

CONCLUSION

Our MRI-based models showed good potential in differentiating Stage I EC from EP and had been validated in multiple centers. Their specificity was higher than that of radiologists and may be used for computer-aided diagnosis in the future to assist clinical diagnosis.

Comparison of a deep learning-accelerated T2-weighted turbo spin echo sequence and its conventional counterpart for female pelvic MRI: reduced acquisition times and improved image quality

OBJECTIVES

To investigate the feasibility of a deep learning-accelerated T2-weighted turbo spin echo (TSE) sequence (T2_DL) applied to female pelvic MRI, using standard T2-weighted TSE (T2_S) as reference.

METHODS

In total, 24 volunteers and 48 consecutive patients with benign uterine diseases were enrolled. Patients in the menstrual phase were excluded. T2_S and T2_DL sequences in three planes were performed for each participant. Quantitative image evaluation was conducted by calculating the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Image geometric distortion was evaluated by measuring the diameters in all three directions of the uterus and lesions. Qualitative image evaluation including overall image quality, artifacts, boundary sharpness of the uterine zonal layers, and lesion conspicuity were assessed by three radiologists using a 5-point Likert scale, with 5 indicating the best quality. Comparative analyses were conducted for the two sequences.

RESULTS

T2_DL resulted in a 62.7% timing reduction (1:54 min for T2_DL and 5:06 min for T2_S in axial, sagittal, and coronal imaging, respectively). Compared to T2_S, T2_DL had significantly higher SNR (p ≤ 0.001) and CNR (p ≤ 0.007), and without geometric distortion (p = 0.925-0.981). Inter-observer agreement regarding qualitative evaluation was excellent (Kendall's W > 0.75). T2_DL provided superior image quality (all p < 0.001), boundary sharpness of the uterine zonal layers (all p < 0.001), lesion conspicuity (p = 0.002, p < 0.001, and p = 0.021), and fewer artifacts (all p < 0.001) in sagittal, axial, and coronal imaging.

CONCLUSIONS

Compared with standard TSE, deep learning-accelerated T2-weighted TSE is feasible to reduce acquisition time of female pelvic MRI with significant improvement of image quality.

Recent Imaging Updates and Advances in Gynecologic Malignancies

Gynecologic malignancies are among the most common cancers in women worldwide and account for significant morbidity and mortality. Management and consequently overall patient survival is reliant upon early detection, accurate staging and early detection of any recurrence. Ultrasound, Computed Tomography (CT), Magnetic resonance imaging (MRI) and Positron Emission Tomography-Computed Tomography (PET-CT) play an essential role in the detection, characterization, staging and restaging of the most common gynecologic malignancies, namely the cervical, endometrial and ovarian malignancies. Recent advances in imaging including functional MRI, hybrid imaging with Positron Emission Tomography (PET/MRI) contribute even more to lesion specification and overall role of imaging in gynecologic malignancies. Radiomics is a neoteric approach which aspires to enhance decision support by extracting quantitative information from radiological imaging.

PET/MR imaging in gynecologic cancer: tips for differentiating normal gynecologic anatomy and benign pathology versus cancer

Positron emission tomography/magnetic resonance imaging (PET/MR) is used in the pre-treatment and surveillance settings to evaluate women with gynecologic malignancies, including uterine, cervical, vaginal and vulvar cancers. PET/MR combines the excellent spatial and contrast resolution of MR imaging for gynecologic tissues, with the functional metabolic information of PET, to aid in a more accurate assessment of local disease extent and distant metastatic disease. In this review, the optimal protocol and utility of whole-body PET/MR imaging in patients with gynecologic malignancies will be discussed, with an emphasis on the advantages of PET/MR over PET/CT and how to differentiate normal or benign gynecologic tissues from cancer in the pelvis.

Diagnostic value of integrated 18F-FDG PET/MRI for staging of endometrial carcinoma: comparison with PET/CT

Purpose

To explore the diagnostic value of integrated positron emission tomography/magnetic resonance imaging (PET/MRI) for the staging of endometrial carcinoma and to investigate the associations between quantitative parameters derived from PET/MRI and clinicopathological characteristics of endometrial carcinoma.

Methods

Altogether, 57 patients with endometrial carcinoma who underwent PET/MRI and PET/computed tomography (PET/CT) preoperatively were included. Diagnostic performance of PET/MRI and PET/CT for staging was compared by three readers. Associations between PET/MRI quantitative parameters of primary tumor lesions and clinicopathological characteristics of endometrial carcinoma were analyzed. Histopathological results were used as the standard.

Results

The overall accuracy of the International Federation of Gynecology and Obstetrics (FIGO) staging for PET/MRI and PET/CT was 86.0% and 77.2%, respectively. PET/MRI had higher accuracy in diagnosing myometrial invasion and cervical invasion and an equivalent accuracy in diagnosing pelvic lymph node metastasis against PET/CT, although without significance. All PET/MRI quantitative parameters were significantly different between stage I and stage III tumors. Only SUV_max/ADC_min were significantly different between stage I and II tumors. No parameters were significantly different between stage II and III tumors. The SUV_max/ADC_min in the receiving operating characteristic (ROC) curve had a higher area under the ROC curve for differentiating stage I tumors and other stages of endometrial carcinoma.

Conclusions

PET/MRI had a higher accuracy for the staging of endometrial carcinoma, mainly for FIGO stage I tumors compared to PET/CT. PET/MRI quantitative parameters, especially SUV_max/ADC_min, were associated with tumor stage and other clinicopathological characteristics. Hence, PET/MRI may be a valuable imaging diagnostic tool for preoperative staging of endometrial carcinoma.

Role of MRI in diagnosing the primary site of origin in indeterminate cases of uterocervical carcinomas: a systematic review and meta-analysis

OBJECTIVE

To perform a literature review assessing role of MRI in predicting origin of indeterminate uterocervical carcinomas with emphasis on sequences and imaging parameters.

METHODS

Electronic literature search of PubMed was performed from its inception until May 2020 and PICO model used for study selection; population was female patients with known/clinical suspicion of uterocervical cancer, intervention was MRI, comparison was by histopathology and outcome was differentiation between primary endometrial and cervical cancers.

RESULTS

Eight out of nine reviewed articles reinforced role of MRI in uterocervical primary determination. T2 and Dynamic contrast were the most popular sequences determining tumor location, morphology, enhancement, and invasion patterns. Role of DWI and MR spectroscopy has been evaluated by even fewer studies with significant differences found in both apparent diffusion coefficient values and metabolite spectra. The four studies eligible for meta-analysis showed a pooled sensitivity of 88.4% (95% confidence interval 70.6 to 96.1%) and a pooled specificity of 39.5% (95% confidence interval 4.2 to 90.6%).

CONCLUSIONS

MRI plays a pivotal role in uterocervical primary determination with both conventional and newer sequences assessing important morphometric and functional parameters. Socioeconomic impact of both primaries, different management guidelines and paucity of existing studies warrants further research. Prospective multicenter trials will help bridge this gap. Meanwhile, individual patient database meta-analysis can help corroborate existing data.

ADVANCES IN KNOWLEDGE

MRI with its classical and functional sequences helps in differentiation of the uterine 'cancer gray zone' which is imperative as both primary endometrial and cervical tumors have different management protocols.

An Application of Machine Learning That Uses the Magnetic Resonance Imaging Metric, Mean Apparent Diffusion Coefficient, to Differentiate between the Histological Types of Ovarian Cancer

This retrospective single-center study included patients diagnosed with epithelial ovarian cancer (EOC) using preoperative pelvic magnetic resonance imaging (MRI). The apparent diffusion coefficient (ADC) of the axial MRI maps that included the largest solid portion of the ovarian mass was analysed. The mean ADC values (ADC_mean) were derived from the regions of interest (ROIs) of each largest solid portion. Logistic regression and three types of machine learning (ML) applications were used to analyse the ADCs and clinical factors. Of the 200 patients, 103 had high-grade serous ovarian cancer (HGSOC), and 97 had non-HGSOC (endometrioid carcinoma, clear cell carcinoma, mucinous carcinoma, and low-grade serous ovarian cancer). The median ADC_mean of patients with HGSOC was significantly lower than that of patients without HGSOCs. Low ADC_mean and CA 19-9 levels were independent predictors for HGSOC over non-HGSOC. Compared to stage I disease, stage III disease was associated with HGSOC. Gradient boosting machine and extreme gradient boosting machine showed the highest accuracy in distinguishing between the histological findings of HGSOC versus non-HGSOC and between the five histological types of EOC. In conclusion, ADC_mean, disease stage at diagnosis, and CA 19-9 level were significant factors for differentiating between EOC histological types.

Usefulness of dynamic contrast-enhanced magnetic resonance imaging in characterizing ovarian tumors classified as indeterminate at ultrasonography

OBJECTIVES

To determine whether there is a significant relationship between the shape of the time-intensity curve on dynamic gadolinium-enhanced magnetic resonance imaging (MRI) of ovarian tumors classified as indeterminate at ultrasonography and the type of lesion (benign, borderline, or malignant) to enable an accurate presurgical diagnosis.

MATERIAL AND METHODS

We used dynamic contrast-enhanced MRI to study 68 ovarian tumors that were classified as indeterminate at ultrasonography. We included only cases for which a definitive diagnosis (histologic diagnosis or ≥1 year stability on imaging tests) was available. Each case was classified as benign, borderline, or malignant. To analyze the MRI studies, we marked regions of interest in the lesion and in the myometrium (as a reference). We obtained a curve defined by the relation between the intensity of enhancement and time and classified each tumor according to four predefined curve types. We also analyzed semiquantitative parameters. Finally, we compared the results for each of the three groups of tumors.

RESULTS

We found significant associations (p <0.001) between the curves without early enhancement and benign and borderline lesions as well as between the curves with early enhancement and malignant lesions. Malignant lesions were significantly associated with the semiquantitative enhancement parameters: maximum (p=0.002), maximum relative (p=0.006), and relative (p=0.018).

CONCLUSIONS

In ovarian tumors classified as indeterminate at ultrasonography, dynamic contrast-enhanced MRI can be useful for classification as benign, borderline, or malignant because the malignant lesions are significantly associated with early enhancement curves.

18F-FDG PET/CT Quantitative Parameters and Texture Analysis Effectively Differentiate Endometrial Precancerous Lesion and Early-Stage Carcinoma

Objective:

This study evaluated the metabolic parameters and texture features of fluorodeoxyglucose positron emission tomography–computed tomography (PET/CT) for the diagnosis and differentiation of endometrial atypical hyperplasia (EAH), EAH with field cancerization (FC), and stage 1A endometrial carcinoma (EC 1a).

Materials and Methods:

We retrospectively analyzed the metabolic parameters of PET/CT in 170 patients with diagnoses confirmed by pathology, including 57 cases of EAH (57/170, 33.53%), 45 cases of FC (45/170, 26.47%), and 68 cases of EC 1a (68/170, 40.0%). Then, the texture features of each tumor were extracted and compared with the metabolic parameters and pathological results using nonparametric tests and linear regression analysis. The diagnostic performance was assessed by the area under the curve (AUC) values obtained from receiver operating characteristic analysis.

Results:

There were moderate positive correlations between the PET standardized uptake values (SUVpeak, SUVmax, and SUVmean) and postoperative pathological features with correlation coefficients (r_s) of 0.663, 0.651, and 0.651, respectively (P < .001). Total lesion glycolysis showed relatively low correlation with pathological characteristics (r_s = 0.476), whereas metabolic tumor volume and age showed the weakest correlations (r_s = 0.186 and 0.232, respectively). To differentiate between the diagnosis of EAH and FC, SUVmax displayed the largest AUC of 0.857 (sensitivity, 82.2%; specificity, 84.2%). Five texture features were screened out as Percentile 40, Percentile 45, InverseDifferenceMoment_AllDirection_offset 1, InverseDifferenceMoment_angle 45_offset 4, and ClusterProminence_angle 135_offset 7 (P < .001) by linear model of texture analysis (AUC = 0.851; specificity = 0.692; sensitivity = 0.871). To differentiate between the diagnoses of FC and EC 1a, SUVpeak displayed the largest AUC of 0.715 (sensitivity, 67.6%; specificity, 77.8%), and 2 texture features were identified as Percentile 10 and CP_angle 135_offset 7 (AUC = 0.819; specificity = 0.871; sensitivity = 0.766; P < .001).

Conclusions:

SUVmax and SUVpeak had the highest diagnostic values for EAH, FC, and EC 1a compared with the other tested parameters. SUVmax, Percentile 40, Percentile 45, InverseDifferenceMoment_AllDirection_offset 1, InverseDifferenceMoment_angle 45_offset 4, and ClusterProminence_angle 135_offset 7 distinguished EAH from FC. SUVpeak, Percentile 10, and ClusterProminence_angle 135_offset 7 distinguished FC from EC 1a. This study showed that the addition of texture features provides valuable information for differentiating EAH, FC, and EC 1a diagnoses.

Locally advanced cervical cancer complicating pregnancy: A case of competing risks from the Catholic University of the Sacred Heart in Rome

A case of stage IB2 cervical cancer at 27 weeks of pregnancy, treated with neoadjuvant chemotherapy followed by radical Cesarean hysterectomy with full pelvic and infra-mesenteric lymphadenectomy, and adjuvant chemo-radiation is described. While she remains without disease, her baby was diagnosed with acute myelogenous leukemia. We highlight the pre-operative work-up, treatment options, safety, feasibility, and outcomes for the mother and her fetus.