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.

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.

Pregnancies after vaginal radical trachelectomy (RT) in patients with early invasive uterine cervical cancer: results from a single institute.

BACKGROUND: Radical tracheletomy (RT) with pelvic lymphadenectomy has become an option for young patients with early invasive uterine cervical cancer who desire to maintain their fertility. However, this operative method entails a high risk for the following pregnancy due to its radicality. METHODS: We have performed vaginal RT for 71 patients and have experienced 28 pregnancies in 21 patients. They were followed up carefully according to the follow-up methods we reported previously. Their pregnancy courses and prognoses after the pregnancy were retrospectively reviewed. RESULTS: All the vaginal RTs were performed safely without serious complications, including 6 patients who underwent the operation during pregnancy. The median time to be pregnant after RT was 29.5 months. 13 patients (46%) became pregnant without artificial insemination by husband or assisted reproductive technology. Cesarean section was performed for all of them. The median time of pregnancy was 34 weeks, and emergent cesarean section was performed for 7 pregnancies (25%). The median birth weight was 2156 g. Four patients had trouble with cervical cerclage, and they suffered from sudden premature preterm rupture of the membrane (pPROM) during the second trimester of pregnancy. We underwent transabdominal cerclage (TAC) for all of them and careful management for the prevention of uterine infection was performed. One patient had a recurrence of cancer during pregnancy. CONCLUSIONS: Both the obstetrical prognosis and oncological prognosis after vaginal RT have become favorable for pregnant patients after vaginal RT.

Multiple part umbilical cord entanglement and neonatal outcomes.

OBJECTIVE: Umbilical cord entanglement is known to be a major cause of fetal hypoxia and to be correlated with several neonatal complications, but almost all of the previous reports were restricted to nuchal cord. In this study, we retrospectively examined the correlation between multiple part cord entanglement and pregnancy outcomes. MATERIALS AND METHODS: A total of 2156 cases were recruited from term deliveries in our hospital from 2008 to 2012. We counted umbilical cord loop numbers not only for nuchal cord but also for trunk and limb cord entanglement. We classified the cases into three groups: no loop, single loop and multiple loops group. We statistically analyzed pregnancy outcomes statistically in the three groups. RESULTS: One thousand, four hundred and fifty-eight cases had no cord entanglement, 594 cases had single loop entanglement and 104 cases had multiple loops entanglement. Values of umbilical artery blood, pH (p = 0.002) and base excess (p < 0.001) showed significantly unfavorable status in entanglement cases, especially in the multiple loops group. A significantly larger percentage of neonates in the multiple loops group needed for oxygen (p < 0.001). CONCLUSION: Multiple umbilical cord entanglement is highly correlated with early neonatal unfavorable status and need for resuscitation.