Uterine myomas are the most common pelvic tumors in women, which can lead to abnormal uterine bleeding, abdominal pain, pelvic compression symptoms, infertility, or adverse pregnancy. In this article, we provide a dataset named uterine myoma MRI dataset (UMD), which can be used for clinical research on uterine myoma imaging. The UMD is the largest publicly available uterine MRI dataset to date including 300 cases of uterine myoma T2-weighted imaging (T2WI) sagittal patient images and their corresponding annotation files. The UMD covers 9 types of uterine myomas classified by the International Federation of Obstetrics and Gynecology (FIGO), which were annotated and reviewed by 11 experienced doctors to ensure the authority of the annotated data. The UMD is helpful for uterine myomas classification and uterine 3D reconstruction tasks, which has important implications for clinical research on uterine myomas.

Uterine myomas affect 70% of women of reproductive age, potentially impacting their fertility and health. Manual film reading is commonly used to identify uterine myomas, but it is time-consuming, laborious, and subjective. Clinical treatment requires the consideration of the positional relationship among the uterine wall, uterine cavity, and uterine myomas. However, due to their complex and variable shapes, the low contrast of adjacent tissues or organs, and indistinguishable edges, accurately identifying them in MRI is difficult. Our work addresses these challenges by proposing an instance segmentation network capable of automatically outputting the location, category, and masks of each organ and lesion. Specifically, we designed a new backbone that facilitates learning the shape features of object diversity, and filters out background noise interference. We optimized the anchor box generation strategy to provide better priors in order to enhance the process of bounding box prediction and regression. An adaptive iterative subdivision strategy ensures that the mask boundary details of objects are more realistic and accurate. We conducted extensive experiments to validate our network, which achieved better average precision (AP) results than those of state-of-the-art instance segmentation models. Compared to the baseline network, our model improved AP on the uterine wall, uterine cavity, and myomas by 8.8%, 8.4%, and 3.2%, respectively. Our work is the first to realize multiclass instance segmentation in uterine MRI, providing a convenient and objective reference for the clinical development of appropriate surgical plans, and has significant value in improving diagnostic efficiency and realizing the automatic auxiliary diagnosis of uterine myomas.

Stewart-treves syndrome (STS) is an angiosarcoma associated with chronic lymphedema. This article analyses the characteristics of twenty-two patients and proposes active intervention in lymphedema and the early diagnosis of STS. Twenty-two patients with STS were diagnosed at the centre over an 11-year period. Clinical manifestations, a series of conventional analyses, and histopathology were used to study these cases retrospectively. The age range of 22 patients with STS was 15 to 78 years. The main clinical manifestations included multiple skin and subcutaneous nodules and scattered red or purplish-red rashes in the lymphoedematous limbs. These patients often showed clinical symptoms such as lymphedema, weakness, emaciation, pain, mass, lymphadenopathy and so on. The positive rates of ultrasonography, MRI and radionuclide imaging were 66.7% (6/9), 92.3% (12/13) and 18.2% (2/11), respectively. The main points regarding active intervention in lymphedema and early diagnosis of STS were summarized. Since this was a retrospective study, the main points summarized by the author need to be further quantified in clinical work to guide the diagnosis of this kind of disease more conveniently. In addition, further clinical trials are needed to evaluate the role of lymphedema in the occurrence and development of malignant tumors. STS can appear in lymphoedematous tissue many years after lymphedema onset. To avoid delays in the diagnosis and therapy of STS, physicians should actively look for signs or symptoms of malignant lymphedema during the follow-up period and promptly manage patients developing problems.

Background: Lower extremity lymphedema (LEL) staging is mainly assessed by systems that solely depend on physical examinations and lack quantitative assessment based on modern imaging. Objective: To explore the value of MRI-based asymmetric volume measurements in the clinical staging of primary LEL. Methods: 92 patients with unilateral primary LEL underwent MRI examinations to determine the volume of the mid-calf (Vcl) calculated using the clinical dermatome method as well as the total volume (Vmri), musculoskeletal volume (VM), and subcutaneous volume (VS) volume of the middle calves. The difference between Vmri (DVmri) and VS (DVS) of the affected and unaffected calves was obtained and defined as the asymmetric volume difference. Meanwhile, the volume of the mid-calf (Vcl) and the difference in volume (DVcl) were calculated using the clinical circumferential method. The relationship between the asymmetric volume difference and clinical staging was then evaluated. Interobserver consistency was assessed through the intraclass correlation coefficient (ICC). Volume comparisons between the three groups were performed using the one-way analysis of variance (ANOVA) or the Kruskal-Wallis test. Spearman’s correlation was used to assess volume and clinical stage correlation. The receiver operating characteristic (ROC) curve was used to evaluate the value of asymmetric volume difference for clinical staging. Results: The asymmetric volume difference was statistically significant in stage I compared to stages II and III (p < 0.05). The asymmetric volume difference (DVmri: r = 0.753; DVS: r = 0.759) correlated more with the clinical stage than the affected Vcl (r = 0.581), Vmri (r = 0.628), VS (r = 0.743), and DVcl (r = 0.718). The area under the ROC curve (AUC) for identifying the clinical stage by the asymmetric volume difference was greater than that for the affected Vcl, Vmri, VS, and DVcl, with DVS (AUC = 0.951) having the largest area under the curve to distinguish between stages I and II. Conclusion: MRI-based asymmetric volume difference is an adjunctive measure for LEL clinical staging with good reproducibility. DVS could be the best indicator for differentiating between stages I and II of primary LEL.

Medical image segmentation algorithms based on deep learning have achieved good segmentation results in recent years, but they require a large amount of labeled data. When performing pixel-level labeling on medical images, labeling a target requires marking ten or even hundreds of points along its edge, which requires a lot of time and labor costs. To reduce the labeling cost, we utilize a click-based interactive segmentation method to generate high-quality segmentation labels. However, in current interactive segmentation algorithms, only the interaction information clicked by the user and the image features are fused as the input of the backbone network (so-called early fusion). The early fusion method has the problem that the interactive information is much sparse at this time. Furthermore, the interactive segmentation algorithms do not take into account the boundary problem, resulting in poor model performance. So we propose early fusion and late fusion strategy to prevent the interaction information from being diluted prematurely and make better use of the interaction information. At the same time, we propose a decoupled head structure, by extracting the image boundary information, and combining the boundary loss function to establish the boundary constraint term, so that the network can pay more attention to the boundary information and further improve the performance of the network. Finally, we conduct experiments on three medical datasets (Chaos, VerSe and Uterine Myoma MRI) to verify the effectiveness of our network. The experimental results show that our network greatly improved compared with the baseline, and NoC@80(the number of interactive clicks over 80% of the IoU threshold) improved by 0.1, 0.1, and 0.2. In particular, we have achieved a NoC@80 score of 1.69 on Chaos. According to statistics, manual annotation takes 25 min to label a case(Uterine Myoma MRI). Annotating a medical image with our method can be done in only 2 or 3 clicks, which can save more than 50% of the cost.