RESUMO
Mucinous cystic neoplasm of the liver (MCN-L) is a rare tumor which accounts for less than 5% of all liver cysts. Although they are considered to be "benign cysts" radiologically and clinically because of their slow growth, they are considered as premalignant. We present two radiologically misdiagnosed cases that operated in a short time range, in order to increase awareness for these rare tumors. A 47-year-old female patient who had no active complaints 58 x 40 mm cystic lesion was detected in the liver, which was diagnosed hydatid cyst radiologically. The pathological examination showed multiloculated cysts which was covered by low-grade mucinous epithelium and ovarian-type stroma on the cyst wall. A 50-year-old female patient presented with abdominal distention. The radiographical screening revealed a 204 x 140 mm cystic lesion that completely fills left lobe of liver which interpreted in favor of hydatid cyst. Histopathologically, the inner surface of the cyst was covered with low grade mucinous epithelium. Ovarian-type stroma was detectable only by immunohistochemistry due to significant bleeding and edema on the wall. The diagnosis of both of our cases was low grade MCN-L. Since cysts were not intact at the time of gross examination, we could not make any comment about surgical margins or total excision. MCN-L is a tumor that creates difficulty in presurgical differential diagnosis because of its rarity and lack of specific radiologic features. Although the prognosis is excellent as a result of total excision in the benign group, relapses have also been reported.
RESUMO
CONTEXT.: Artificial intelligence algorithms hold the potential to fundamentally change many aspects of society. Application of these tools, including the publicly available ChatGPT, has demonstrated impressive domain-specific knowledge in many areas, including medicine. OBJECTIVES.: To understand the level of pathology domain-specific knowledge for ChatGPT using different underlying large language models, GPT-3.5 and the updated GPT-4. DESIGN.: An international group of pathologists (n = 15) was recruited to generate pathology-specific questions at a similar level to those that could be seen on licensing (board) examinations. The questions (n = 15) were answered by GPT-3.5, GPT-4, and a staff pathologist that recently passed their Canadian pathology licensing exams. Participants were instructed to score answers on a 5-point scale and to predict which answer was written by ChatGPT. RESULTS.: GPT-3.5 performed at a similar level to the staff pathologist, while GPT-4 outperformed both. The overall score for both GPT-3.5 and GPT-4 was within the range of meeting expectations for a trainee writing licensing examinations. In all but one question, the reviewers were able to correctly identify the answers generated by GPT-3.5. CONCLUSIONS.: By demonstrating the ability of ChatGPT to answer pathology-specific questions at a level similar to (GPT-3.5) or exceeding (GPT-4) a trained pathologist, this study highlights the potential of large language models to be transformative in this space. In the future, more advanced iterations of these algorithms with increased domain-specific knowledge may have the potential to assist pathologists and enhance pathology resident training.
RESUMO
The utility of histological grading, which is useful in predicting prognosis in many tumors, is controversial for oral squamous cell carcinoma (OSCC). Therefore, new histopathological parameters should be added to histopathology reports of OSCCs. The study aimed to evaluate the parameters of worst invasion pattern (WPOI) and tumor budding in patients with OSCC, to compare them with other histopathological parameters, clinical data and overall survival, and to evaluate these results within the literature. A total of 73 OSCC cases with excisional biopsies were included in this study. WPOI, tumor budding, cell nest size, tumor-stroma ratio, stromal lymphocyte infiltration and stroma type, as well as classical histopathological parameters, were evaluated on hematoxylin-eosin-stained sections. Perineural invasion, lymph node metastases, advanced stage, presence of more than five buds and single cell invasion pattern in univariate survival analyses are characterized by a shortened overall survival time. While there was no significant difference between WPOI results and survival in the survival analysis, WPOI 5 was associated with more frequent lymph node metastasis and advanced stage at the time of diagnosis compared to WPOI 4. We concluded that tumor budding and single-cell invasion should be considered prognostic histopathologic parameters in OSCC.
