Endometrial cancer is a ubiquitous gynecological disease with increasing global incidence. Therefore, despite the lack of an established screening technique to date, early diagnosis of endometrial cancer assumes critical importance. This paper presents an artificial-intelligence-based system to detect the regions affected by endometrial cancer automatically from hysteroscopic images. In this study, 177 patients (60 with normal endometrium, 21 with uterine myoma, 60 with endometrial polyp, 15 with atypical endometrial hyperplasia, and 21 with endometrial cancer) with a history of hysteroscopy were recruited. Machine-learning techniques based on three popular deep neural network models were employed, and a continuity-analysis method was developed to enhance the accuracy of cancer diagnosis. Finally, we investigated if the accuracy could be improved by combining all the trained models. The results reveal that the diagnosis accuracy was approximately 80% (78.91–80.93%) when using the standard method, and it increased to 89% (83.94–89.13%) and exceeded 90% (i.e., 90.29%) when employing the proposed continuity analysis and combining the three neural networks, respectively. The corresponding sensitivity and specificity equaled 91.66% and 89.36%, respectively. These findings demonstrate the proposed method to be sufficient to facilitate timely diagnosis of endometrial cancer in the near future.

Toyohara Y, et al. J Gynecol Oncol. 2023 Dec;35:e24. https://doi.org/10.3802/jgo.2024.35.e24

Purpose: Recurrent implantation failure (RIF) is a form of refractory infertility that persists despite assisted reproductive technology. Cine magnetic resonance imaging (cine MRI) enables the visualization of uterine peristalsis; however, its use in RIF assessment is limited due to the lack of a standardized application method. This study aimed to develop pregnancy prediction models for patients with RIF and to evaluate the utility of cine MRI image analysis using artificial intelligence (AI). Methods: We retrospectively analyzed the anonymized clinical data and cine MRI images of 188 patients with RIF and known pregnancy outcomes. Two types of models, based on clinical data only or both clinical data and cine MRI images, were built using the Random Forest model. The best model was identified using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. Results: Higher performance was achieved using the Random Forest model integrating clinical data and cine MRI images (AUC/accuracy/sensitivity/specificity: 0.835, 0.754, 0.879, and 0.583, respectively), outperforming models using clinical data only (0.617, 0.596, 0.697, and 0.458, respectively). Conclusions: AI analysis of clinical data combined with cine MRI data improved pregnancy prediction, suggesting that cine MRI can be used to evaluate uterine factor‐related RIF.

Surgical treatment is the only option for cholesteatoma; however, the recurrence rate is high, and the incidence of residual cholesteatoma recurrence largely depends on the surgeon's skill. Training deep neural network (DNN) models typically requires large datasets, but the prevalence of cholesteatoma is low (1 in 25,000 people). However, cholesteatoma remains difficult to treat. Developing analytical methods to improve ac-curacy with limited datasets remains a significant challenge in medical artificial intelli-gence (AI) research. This study introduces an AI-based system for detecting residual cholesteatoma in surgical field videos. A retrospective analysis was conducted on 144 cases from 88 patients who underwent surgery. The training dataset comprised videos of cholesteatoma lesions recorded during surgery and intact middle ear mucosa after lesion removal. These videos were captured using both endoscope and microscope for AI model development. The diagnostic accuracy was approximately 80% for both endoscopic and microscopic images. Although the diagnostic accuracy for microscopic images was slightly lower, focusing on the lesion center improved the accuracy to a level comparable to that of endoscopic images. This study demonstrates the diagnostic feasibility of AI-based cholesteatoma detection despite a limited sample size highlighting the value of proof-of-concept studies in clar-ifying technical requirements for future clinical systems and is the first AI study to use videos from both modalities.

Surgical treatment is the only option for cholesteatoma; however, the recurrence rate is high, and the incidence of residual cholesteatoma recurrence largely depends on the surgeon’s skill. Training deep neural network (DNN) models typically requires large datasets, but the prevalence of cholesteatoma is low (1 in 25,000 people). It also remains difficult to treat. Developing analytical methods to improve accuracy with limited datasets remains a significant challenge in medical artificial intelligence (AI) research. This study introduces an AI-based system for detecting residual cholesteatoma in surgical field videos. A retrospective analysis was conducted on 144 cases from 88 patients who underwent surgery. The training dataset comprised videos of cholesteatoma lesions recorded during surgery and intact middle ear mucosa after lesion removal. These videos were captured using both an endoscope and a surgical microscope for AI model development. The diagnostic accuracy was approximately 80% for both endoscopic and microscopic images. Although the diagnostic accuracy for microscopic images was slightly lower, focusing on the lesion center improved the accuracy to a level comparable to that of endoscopic images. This study demonstrates the diagnostic feasibility of AI-based cholesteatoma detection despite a limited sample size, highlighting the value of proof-of-concept studies in clarifying technical requirements for future clinical systems. To our knowledge, this is the first AI study to use videos from both modalities.