Huimin An

Background: Chat Generative Pretrained Transformer (ChatGPT) is a type of large language model (LLM) developed by OpenAI, known for its extensive knowledge base and interactive capabilities. These attributes make it a valuable tool in the medical field, particularly for tasks such as answering medical questions, drafting clinical notes, and optimizing the generation of radiology reports. However, keeping accuracy in medical contexts is the biggest challenge to employing GPT-4 in a clinical setting. This study aims to investigate the accuracy of GPT-4, which can process both text and image inputs, in generating diagnoses from pathological images.Methods: This study analyzed 44 histopathological images from 16 organs and 100 colorectal biopsy photomicrographs. The initial evaluation was conducted using the standard GPT-4 model in January 2024, with a subsequent re-evaluation performed in July 2024. The diagnostic accuracy of GPT-4 was assessed by comparing its outputs to a reference standard using statistical measures. Additionally, four pathologists independently reviewed the same images to compare their diagnoses with the model’s outputs. Both scanned and photographed images were tested to evaluate GPT-4’s generalization ability across different image types.Results: GPT-4 achieved an overall accuracy of 0.64 in identifying tumor imaging and tissue origins. For colon polyp classification, accuracy varied from 0.57 to 0.75 in different subtypes. The model achieved 0.88 accuracy in distinguishing low-grade from high-grade dysplasia and 0.75 in distinguishing high-grade dysplasia from adenocarcinoma, with a high sensitivity in detecting adenocarcinoma. Consistency between initial and follow-up evaluations showed slight to moderate agreement, with Kappa values ranging from 0.204 to 0.375.Conclusion: GPT-4 demonstrates the ability to diagnose pathological images, showing improved performance over earlier versions. Its diagnostic accuracy in cancer is comparable to that of pathology residents. These findings suggest that GPT-4 holds promise as a supportive tool in pathology diagnostics, offering the potential to assist pathologists in routine diagnostic workflows.

Rationale: Ichthyosis uteri is a rare pathological condition characterized by the replacement of the endometrial lining by stratified squamous epithelium. Yet its occurrence with endometrial adenocarcinoma is very rare. Patient concerns: A 68-year-old woman has been experiencing sporadic, minor vaginal hemorrhages for a few months. The gynecological evaluation revealed a uterine enlargement and imaging demonstrated an irregular mass within the uterus. Diagnosis: Endometrial adenocarcinoma with transitional cell differentiation; ichthyosis uteri with dysplasia. Interventions: Radical hysterectomy with pelvic lymphadenectomy was performed followed by postoperative radiotherapy. Outcomes: Postoperative follow-up at 8 months showed a favorable outcome without signs of recurrence and metastasis. Lessons: Adequate pathological sampling is crucial to identifying the accompanying lesions of ichthyosis uteri. Finding molecular alterations in various pathological morphologies is important to understand the evolution of disease.

Cervical squamous intraepithelial lesions (SILs) are precursor lesions of cervical cancer, and their accurate diagnosis enables patients to be treated before malignancy manifests. However, the identification of SILs is usually laborious and has low diagnostic consistency due to the high similarity of pathological SIL images. Although artificial intelligence (AI), especially deep learning algorithms, has drawn a lot of attention for its good performance in cervical cytology tasks, the use of AI for cervical histology is still in its early stages. The feature extraction, representation capabilities, and use of p16 immunohistochemistry (IHC) among existing models are inadequate. Therefore, in this study, we first designed a squamous epithelium segmentation algorithm and assigned the corresponding labels. Second, p16-positive area of IHC slides were extracted with Whole Image Net (WI-Net), followed by mapping the p16-positive area back to the H&E slides and generating a p16-positive mask for training. Finally, the p16-positive areas were inputted into Swin-B and ResNet-50 to classify the SILs. The dataset comprised 6171 patches from 111 patients; patches from 80% of the 90 patients were used for the training set. The accuracy of the Swin-B method for high-grade squamous intraepithelial lesion (HSIL) that we propose was 0.914 [0.889–0.928]. The ResNet-50 model for HSIL achieved an area under the receiver operating characteristic curve (AUC) of 0.935 [0.921–0.946] at the patch level, and the accuracy, sensitivity, and specificity were 0.845, 0.922, and 0.829, respectively. Therefore, our model can accurately identify HSIL, assisting the pathologist in solving actual diagnostic issues and even directing the follow-up treatment of patients.