Prediction of Mismatch Repair Status in Endometrial Cancer from Histological Slide Images Using Various Deep Learning-Based Algorithms.

The application of deep learning algorithms to predict the molecular profiles of various cancers from digital images of hematoxylin and eosin (H&E)-stained slides has been reported in recent years, mainly for gastric and colon cancers. In this study, we investigated the potential use of H&E-stained endometrial cancer slide images to predict the associated mismatch repair (MMR) status. H&E-stained slide images were collected from 127 cases of the primary lesion of endometrial cancer. After digitization using a Nanozoomer virtual slide scanner (Hamamatsu Photonics), we segmented the scanned images into 5397 tiles of 512 × 512 pixels. The MMR proteins (PMS2, MSH6) were immunohistochemically stained, classified into MMR proficient/deficient, and annotated for each case and tile. We trained several neural networks, including convolutional and attention-based networks, using tiles annotated with the MMR status. Among the tested networks, ResNet50 exhibited the highest area under the receiver operating characteristic curve (AUROC) of 0.91 for predicting the MMR status. The constructed prediction algorithm may be applicable to other molecular profiles and useful for pre-screening before implementing other, more costly genetic profiling tests.

Pregnancy-specific beta-1-glycoprotein 6 is a potential novel diagnostic biomarker of placenta accreta spectrum.

Early diagnosis is essential for the safer perinatal management of placenta accreta spectrum (PAS). We used transcriptome analysis to investigate diagnostic maternal serum biomarkers and the mechanisms of PAS development. We analyzed eight formalin-fixed paraffin-embedded placental specimens from two placenta increta and three placenta percreta cases who underwent cesarean hysterectomy at Sapporo Medical University Hospital between 2013 and 2019. Invaded placental regions were isolated from the uterine myometrium and RNA was extracted. The transcriptome difference between normal placenta and PAS was analyzed by microarray analysis. The PAS group showed markedly decreased expression of placenta-specific genes such as LGALS13 and the pregnancy-specific beta-1-glycoprotein (PSG) family. Term enrichment analysis revealed changes in genes related to cellular protein catabolic process, female pregnancy, autophagy, and metabolism of lipids. From the highly dysregulated genes in the PAS group, we investigated the expression of PSG family members, which are secreted into the intervillous space and can be detected in maternal serum from the early stage of pregnancy. The gene expression level of PSG6 in particular was progressively decreased from placenta increta to percreta. The PSG family, especially PSG6, is a potential biomarker for PAS diagnosis.

A screening assistance system for cervical cytology of squamous cell atypia based on a two-step combined CNN algorithm with label smoothing.

BACKGROUND: Although many cervical cytology diagnostic support systems have been developed, it is challenging to classify overlapping cell clusters with a variety of patterns in the same way that humans do. In this study, we developed a fast and accurate system for the detection and classification of atypical cell clusters by using a two-step algorithm based on two different deep learning algorithms. METHODS: We created 919 cell images from liquid-based cervical cytological samples collected at Sapporo Medical University and annotated them based on the Bethesda system as a dataset for machine learning. Most of the images captured overlapping and crowded cells, and images were oversampled by digital processing. The detection system consists of two steps: (1) detection of atypical cells using You Only Look Once v4 (YOLOv4) and (2) classification of the detected cells using ResNeSt. A label smoothing algorithm was used for the dataset in the second classification step. This method annotates multiple correct classes from a single cell image with a smooth probability distribution. RESULTS: The first step, cell detection by YOLOv4, was able to detect all atypical cells above ASC-US without any observed false negatives. The detected cell images were then analyzed in the second step, cell classification by the ResNeSt algorithm, which exhibited average accuracy and F-measure values of 90.5% and 70.5%, respectively. The oversampling of the training image and label smoothing algorithm contributed to the improvement of the system's accuracy. CONCLUSION: This system combines two deep learning algorithms to enable accurate detection and classification of cell clusters based on the Bethesda system, which has been difficult to achieve in the past. We will conduct further research and development of this system as a platform for augmented reality microscopes for cytological diagnosis.

Obstetrical prognosis of patients who underwent vaginal radical trachelectomy during pregnancy.

AIM: Radical trachelectomy (RT) with pelvic lymphadenectomy has become an option for young patients with early invasive uterine cervical cancer who decide to maintain their fertility. However, this operative method entails a high risk for the following pregnancy due to its radicality. Therefore, RT for pregnant patients can be a challenge both for gynecologic oncologists and obstetricians. METHODS: We have performed vaginal RT for five pregnant patients with uterine cervical cancer stage 1B1 according to the method of Dargent et al. The operations were performed between 16 and 26 weeks of pregnancy, and the patients were followed up carefully according to the follow-up methods we reported previously. RESULTS: Vaginal RT was performed for five patients without any troubles. Four of the patients continued their pregnancies until almost 34 weeks or longer under our previously published follow-up schedule. The pregnancy of one patient was terminated at 26 weeks due to recurrence of the cancer. CONCLUSION: Expansion of vaginal RT for pregnant patients with uterine cervical cancer could be a practical option for pregnant patients with early invasive uterine cervical cancer.

Recurrent Massive Uterine Bleeding from a Cesarean Scar Treated Successfully by Laparoscopic Surgery.

A cesarean scar can cause abnormal uterine bleeding including prolonged menstruation or postmenstrual spotting. Our patient showed massive uterine bleeding from a cesarean scar and needed blood transfusion for hemorrhagic shock. A cesarean section had only been performed once for delivery stop 9 years ago. Recurrent hemorrhage could not be controlled by conservative treatment, and we performed laparoscopic scar resection and repair. The abnormal uterine bleeding was successfully stopped, and the menstrual cycle was normalized after surgical treatment. We should be aware that even an uneventful cesarean section may have a risk of massive hemorrhage postoperatively as in the present case.