Advances in the Preoperative Identification of Uterine Sarcoma

The automatic diagnosis artificial intelligence system for preoperative magnetic resonance imaging of uterine sarcoma

OBJECTIVE

Magnetic resonance imaging (MRI) is efficient for the diagnosis of preoperative uterine sarcoma; however, misdiagnoses may occur. In this study, we developed a new artificial intelligence (AI) system to overcome the limitations of requiring specialists to manually process datasets and a large amount of computer resources.

METHODS

The AI system comprises a tumor image filter, which extracts MRI slices containing tumors, and sarcoma evaluator, which diagnoses uterine sarcomas. We used 15 types of MRI patient sequences to train deep neural network (DNN) models used by tumor filter and sarcoma evaluator with 8 cross-validation sets. We implemented tumor filter and sarcoma evaluator using ensemble prediction technique with 9 DNN models. Ten tumor filters and sarcoma evaluator sets were developed to evaluate fluctuation accuracy. Finally, AutoDiag-AI was used to evaluate the new validation dataset, including 8 cases of sarcomas and 24 leiomyomas.

RESULTS

Tumor image filter and sarcoma evaluator accuracies were 92.68% and 90.50%, respectively. AutoDiag-AI with the original dataset accuracy was 89.32%, with 90.47% sensitivity and 88.95% specificity, whereas AutoDiag-AI with the new validation dataset accuracy was 92.44%, with 92.25% sensitivity and 92.50% specificity.

CONCLUSION

Our newly established AI system automatically extracts tumor sites from MRI images and diagnoses them as uterine sarcomas without human intervention. Its accuracy is comparable to that of a radiologist. With further validation, the system could be applied for diagnosis of other diseases. Further improvement of the system's accuracy may enable its clinical application in the future.

A rare case report of low-grade endometrial sarcoma: A surgical tale from Himalayas

INTRODUCTION

In the context of female genital tract malignancy, uterine sarcoma is considered the rarest form of the disease. Despite the inert nature of low-grade endometrial sarcoma, they must be meticulously diagnosed on time, with an exact grading of the severity and staging of the disease, which further guides the treatment modality and prognosis.

CASE SUMMARY

A married Asian female without any significant past medical and surgical history complained of abdominal distension and discomfort, which was progressive in nature, for which a radiological assessment was made that showed features suggestive of endometrial sarcoma. Total abdominal hysterectomy with sapingoopherectomy was done without any perioperative complications. Histology further confirmed the diagnosis. Post-operatively, the patient had an unremarkable hospital stay and was discharged home.

DISCUSSION

Endometrial stromal sarcoma is one of the rare malignant entities presenting usually in late adult females, but sometimes it can present at an earlier age as well. Abdominal masses in females, although usually overlooked as benign, can sometimes be associated with a malignant picture. Low-grade endometrial sarcomas have been seen to masquerade other minor benign cases, such as leiomyoma. Despite the rarity of such malignant conditions, diagnosis and management are rather straightforward, and post-operative patient prognosis has been found to be rewarding.

CONCLUSION

Among the uterine sarcoma cases, endometrial sarcoma comes under the malignant disease of the least occurrence. Compared to other malignant conditions, these patients present with minor symptoms like discomfort, which may go unchecked. The major factor that should be noted is the on-time diagnosis and appropriate choice of treatment modality. Overall, despite a minute prevalence and difficult diagnosis, the prognosis of the patient is rather good.

Management of Uterine Fibroids and Sarcomas: The Palermo Position Paper

BACKGROUND

Uterine fibroids are benign monoclonal tumors originating from the smooth muscle cells of the myometrium, constituting the most prevalent pathology within the female genital tract. Uterine sarcomas, although rare, still represent a diagnostic challenge and should be managed in centers with adequate expertise in gynecological oncology.

OBJECTIVES

This article is aimed to summarize and discuss cutting-edge elements about the diagnosis and management of uterine fibroids and sarcomas.

METHODS

This paper is a report of the lectures presented in an expert meeting about uterine fibroids and sarcomas held in Palermo in February 2023.

OUTCOME

Overall, the combination of novel molecular pathways may help combine biomarkers and expert ultrasound for the differential diagnosis of uterine fibroids and sarcomas. On the one hand, molecular and cellular maps of uterine fibroids and matched myometrium may enhance our understanding of tumor development compared to histologic analysis and whole tissue transcriptomics, and support the development of minimally invasive treatment strategies; on the other hand, ultrasound imaging allows in most of the cases a proper mapping the fibroids and to differentiate between benign and malignant lesions, which need appropriate management.

CONCLUSIONS AND OUTLOOK

The choice of uterine fibroid management, including pharmacological approaches, surgical treatment, or other strategies, such as high-intensity focused ultrasound (HIFU), should be carefully considered, taking into account the characteristics of the patient and reproductive prognosis.

Leiomyoma or sarcoma? MRI performance in the differential diagnosis of sonographically suspicious uterine masses

PURPOSE

To assess the diagnostic performance of MRI in distinguishing between leiomyomas and malignant/potentially malignant mesenchymal neoplasms in patients with rapidly enlarging/sonographically suspicious uterine masses.

METHODS

IRB-approved retrospective study including 88 patients (51 ± 11 years) who underwent MRI for rapidly enlarging/sonographically suspicious uterine mass at our Institution between January 2016 and December 2021, followed by surgery or >12 months follow-up. Qualitative image analysis was independently performed by 2 radiologists and included lesion's margins (sharp/irregular), architecture (homogeneous/inhomogeneous), presence of endometrial infiltration (yes/no), necrotic areas (yes/no), hemorrhagic areas (yes/no), predominant signal intensity on T1-WI, T2-WI, CE T1-WI, DWI, and ADC map. The same radiologists performed quantitative image analysis in consensus, which included lesion's maximum diameter, lesion/myometrium signal intensity ratio on T2-WI and CE T1-weighted images, lesion/endometrium signal intensity ratio on DWI and ADC map and necrosis percentage. Lesions were classified as benign or malignant. Imaging findings were compared with pathology and/or follow-up.

RESULTS

After surgery (52/88 patients) or follow-up (36/88 patients, 33 ± 20 months), 83/88 (94.3%) lesions were classified as benign and 5/88 (5.7%) as malignant/potentially malignant. Presence of necrotic areas, high necrosis percentage, hyperintensity on DWI and high lesion/endometrium DWI signal intensity ratio were significantly associated with malignant/potentially malignant lesions (p = 0.027, 0.002, 0.008 and 0.015, respectively). The two readers identified malignant/potentially malignant lesions with 95.5% accuracy, 80.0% sensitivity, 96.4% specificity, 57.1 % PPV, 93.3% NPV.

CONCLUSION

MRI has high accuracy in identifying malignant/potentially malignant myometrial masses. In everyday practice, however, MRI positive predictive value is relatively low given the low pre-test malignancy probability.

A human-interpretable machine learning pipeline based on ultrasound to support leiomyosarcoma diagnosis

The preoperative evaluation of myometrial tumors is essential to avoid delayed treatment and to establish the appropriate surgical approach. Specifically, the differential diagnosis of leiomyosarcoma (LMS) is particularly challenging due to the overlapping of clinical, laboratory and ultrasound features between fibroids and LMS. In this work, we present a human-interpretable machine learning (ML) pipeline to support the preoperative differential diagnosis of LMS from leiomyomas, based on both clinical data and gynecological ultrasound assessment of 68 patients (8 with LMS diagnosis). The pipeline provides the following novel contributions: (i) end-users have been involved both in the definition of the ML tasks and in the evaluation of the overall approach; (ii) clinical specialists get a full understanding of both the decision-making mechanisms of the ML algorithms and the impact of the features on each automatic decision. Moreover, the proposed pipeline addresses some of the problems concerning both the imbalance of the two classes by analyzing and selecting the best combination of the synthetic oversampling strategy of the minority class and the classification algorithm among different choices, and the explainability of the features at global and local levels. The results show very high performance of the best strategy (AUC = 0.99, F1 = 0.87) and the strong and stable impact of two ultrasound-based features (i.e., tumor borders and consistency of the lesions). Furthermore, the SHAP algorithm was exploited to quantify the impact of the features at the local level and a specific module was developed to provide a template-based natural language (NL) translation of the explanations for enhancing their interpretability and fostering the use of ML in the clinical setting.

Contained Power Morcellation in Laparoscopic Uterine Myoma Surgeries: A Brief Review

Uterine fibromas are the most common benign uterine tumors. Although the majority of leiomyomas remain asymptomatic, they can cause serious clinical problems, including abnormal uterine bleeding, pelvic pain, and infertility, which require effective gynecological intervention. Depending on the symptoms as well as patients' preferences, various treatment options are available, such as medical therapy, non-invasive procedures, and surgical methods. Regardless of the extent of the surgery, the preferred option is the laparoscopic approach. To reduce the risk of spreading occult malignancy and myometrial cells associated with fragmentation of the specimen before its removal from the peritoneal cavity, special systems for laparoscopic contained morcellation have been developed. The aim of this review is to present the state-of-the-art contained morcellation. Different types of available retrieval bags are demonstrated. The advantages and difficulties associated with contained morcellation are described. The impact of retrieval bag usage on the course of surgery, as well as the effects of the learning curve, are discussed. The role of contained morcellation in the overall strategy to optimize patient safety is highlighted.

Rapidly growing uterine myoma - should we be afraid of it?

During a year, myomas may undergo radical changes in their dimensions - from decreasing by 90% to growing by 200%. On average, myomas of the uterus increase in volume by 20-30% annually in the premenopausal period. On the other hand, myomas regress spontaneously in about 20% of women. After menopause uterine fibroids stabilize or regress. Every new or growing lesion of the uterus after menopause has to be diagnosed. There is no general definition of fast growing uterine myoma. The presence of fast growing uterine myoma, regardless of its definition, is associated with some clinical issues: it may become symptomatic (pain, bleeding, bulk symptoms), may be responsible for infertility, and a malignant process (leiomyosarcoma) may be present. Regardless of common belief, the risk of sarcoma is not related to the size of the uterus or its fast enlargement. The prevalence of sarcoma in myomas is 0.26%, and in rapidly growing myomas is 0.27%. Treatment should be individualized, selected for the age of the woman and her expectations (preservation of fertility, uterus), symptoms, size and localization of the myomas. The methods of surgical treatment of unsuspected "rapidly growing myomas" are the same as those of common uterine fibroids. Minimally invasive surgery is optimal, but a decision has to be made after evaluation of the risk factors of sarcoma.

The Role of Hyperthermic Intraperitoneal Chemotherapy in Uterine Cancer Therapy

Endometrial cancer and uterine sarcoma represent the two major types of uterine cancer. In advanced stages, both cancer entities are challenging to treat and correlate with a meagre survival and prognosis. Hyperthermic Intraperitoneal Chemotherapy (HIPEC) is a form of localized chemotherapy that is heated to improve the chemotherapeutic effect on peritoneal metastases. The aim of the current review is to study the role of HIPEC in the treatment of uterine cancer. A literature review was conducted using the MEDLINE and LIVIVO databases with a view to identifying relevant studies. By employing the search terms "hyperthermic intraperitoneal chemotherapy", "uterine cancer", "endometrial cancer", and/or "uterine sarcoma", we managed to identify 26 studies published between 2004 and 2023. The present work embodies the most up-to-date, comprehensive review of the literature centering on the particular role of HIPEC as treatment modality for peritoneally metastasized uterine cancer. Patients treated with cytoreductive surgery, alongside HIPEC, seem to profit from not only higher survival but also lower recurrence rates. Factors such as the completeness of cytoreductive surgery, the peritoneal cancer index, the histologic subtype, or the applied chemotherapeutic agent, all influence HIPEC therapy effectiveness. In summary, HIPEC seems to represent a promising treatment alternative for aggressive uterine cancer.

Automated Uterine Fibroids Detection in Ultrasound Images Using Deep Convolutional Neural Networks

Fibroids of the uterus are a common benign tumor affecting women of childbearing age. Uterine fibroids (UF) can be effectively treated with earlier identification and diagnosis. Its automated diagnosis from medical images is an area where deep learning (DL)-based algorithms have demonstrated promising results. In this research, we evaluated state-of-the-art DL architectures VGG16, ResNet50, InceptionV3, and our proposed innovative dual-path deep convolutional neural network (DPCNN) architecture for UF detection tasks. Using preprocessing methods including scaling, normalization, and data augmentation, an ultrasound image dataset from Kaggle is prepared for use. After the images are used to train and validate the DL models, the model performance is evaluated using different measures. When compared to existing DL models, our suggested DPCNN architecture achieved the highest accuracy of 99.8 percent. Findings show that pre-trained deep-learning model performance for UF diagnosis from medical images may significantly improve with the application of fine-tuning strategies. In particular, the InceptionV3 model achieved 90% accuracy, with the ResNet50 model achieving 89% accuracy. It should be noted that the VGG16 model was found to have a lower accuracy level of 85%. Our findings show that DL-based methods can be effectively utilized to facilitate automated UF detection from medical images. Further research in this area holds great potential and could lead to the creation of cutting-edge computer-aided diagnosis systems. To further advance the state-of-the-art in medical imaging analysis, the DL community is invited to investigate these lines of research. Although our proposed innovative DPCNN architecture performed best, fine-tuned versions of pre-trained models like InceptionV3 and ResNet50 also delivered strong results. This work lays the foundation for future studies and has the potential to enhance the precision and suitability with which UF is detected.

Metastatic Uterine Leiomyosarcoma as a Rare and Sinister Cause of Respiratory Distress: A Case Report and Literature Review

Uterine leiomyosarcomas are an extremely rare subtype of uterine malignancy. This is a case report of a 47-year-old woman whose underlying uterine leiomyosarcoma manifested as acute respiratory distress secondary to pulmonary metastases. We highlight that a combination of suggestive imaging features and elevated lactate dehydrogenase (LDH) may prompt its diagnosis, notwithstanding that histological examination of a tissue sample is mandatory for its confirmation. The diagnosis of this condition is arduous for a multitude of reasons, including the insidious clinical course, aggressive nature, and high propensity to metastasize, coupled with a lack of standardised guidelines for its preoperative work-up. These challenges are amplified where resources may be limited, such as in the Caribbean region, where radiographic imaging and treatment options may not always be readily available.

The Role of MicroRNAs in Uterine Leiomyosarcoma Diagnosis and Treatment

Uterine sarcomas are rare gynecological tumors arising from the myometrium or the connective tissue of the endometrium with a relatively poor prognosis. MicroRNAs (miRNAs) represent small, single-stranded, non-coding RNA molecules that can function as oncogenes or tumor suppressors under certain conditions. The current review aims at studying the role of miRNAs in uterine sarcoma diagnosis and treatment. In order to identify relevant studies, a literature review was conducted using the MEDLINE and LIVIVO databases. The search terms "microRNA" and "uterine sarcoma" were employed, and we were able to identify 24 studies published between 2008 and 2022. The current manuscript represents the first comprehensive review of the literature focusing on the particular role of miRNAs as biomarkers for uterine sarcomas. miRNAs were found to exhibit differential expression in uterine sarcoma cell lines and interact with certain genes correlating with tumorigenesis and cancer progression, whereas selected miRNA isoforms seem to be either over- or under-expressed in uterine sarcoma samples compared to normal uteri or benign tumors. Furthermore, miRNA levels correlate with various clinical prognostic parameters in uterine sarcoma patients, whereas each uterine sarcoma subtype is characterized by a unique miRNA profile. In summary, miRNAs seemingly represent novel trustworthy biomarkers for the diagnosis and treatment of uterine sarcoma.

Overlap of Suspicious and Non-Suspicious Features in the Ultrasound Evaluations of Leiomyosarcoma: A Single-Center Experience

Leiomyosarcoma (LMS) is a rare type of mesenchymal tumor. Suspecting LMS before surgery is crucial for proper patient management. Ultrasound is the primary method for assessing myometrial lesions. The overlapping of clinical, laboratory, as well as ultrasound features between fibroids and LMS makes differential diagnosis difficult. We report our single-center experience in ultrasound imaging assessment of LMS patients, highlighting that misleading findings such as shadowing and absent or minimal vascularization may also occur in LMS. To avoid mistakes, a comprehensive evaluation of potentially overlapping ultrasound features is necessary in preoperative ultrasound evaluations of all myometrial tumors.