Background: Accurate classification of breast cancer molecular subtypes is crucial in determining treatment strategies and predicting clinical outcomes. This classification largely depends on the assessment of human epidermal growth factor receptor 2 (HER2), estrogen receptor (ER), and progesterone receptor (PR) status. However, variability in interpretation among pathologists pose challenges to the accuracy of this classification. This study evaluates the role of artificial intelligence (AI) in enhancing the consistency of these evaluations. Methods: AI-powered HER2 and ER/PR analyzers, consisting of cell and tissue models, were developed using 1,259 HER2, 744 ER, and 466 PR-stained immunohistochemistry (IHC) whole-slide images of breast cancer. External validation cohort comprising HER2, ER, and PR IHCs of 201 breast cancer cases were analyzed with these AI-powered analyzers. Three board-certified pathologists independently assessed these cases without AI annotation. Then, cases with differing interpretations between pathologists and the AI analyzer were revisited with AI assistance, focusing on evaluating the influence of AI assistance on the concordance among pathologists during the revised evaluation compared to the initial assessment. Results: Reevaluation was required in 61 (30.3%), 42 (20.9%), and 80 (39.8%) of HER2, in 15 (7.5%), 17 (8.5%), and 11 (5.5%) of ER, and in 26 (12.9%), 24 (11.9%), and 28 (13.9%) of PR evaluations by the pathologists, respectively. Compared to initial interpretations, the assistance of AI led to a notable increase in the agreement among three pathologists on the status of HER2 (from 49.3 to 74.1%, p < 0.001), ER (from 93.0 to 96.5%, p = 0.096), and PR (from 84.6 to 91.5%, p = 0.006). This improvement was especially evident in cases of HER2 2+ and 1+, where the concordance significantly increased from 46.2 to 68.4% and from 26.5 to 70.7%, respectively. Consequently, a refinement in the classification of breast cancer molecular subtypes (from 58.2 to 78.6%, p < 0.001) was achieved with AI assistance. Conclusions: This study underscores the significant role of AI analyzers in improving pathologists' concordance in the classification of breast cancer molecular subtypes.

Rationale: Renal cell carcinoma (RCC) is the most common renal neoplasm, accounting for 2.4% of all cancers in Korea. Although the usual clinical manifestations of RCC include flank pain, hematuria, and palpable mass, RCC is generally characterized by a lack of early warning signs and is mostly discovered incidentally in advanced stage. This case report describes a 42-year-old Korean man diagnosed with giant RCC who presented with simple back pain. Patient concerns: The clinical manifestation of a 42-year-old Korean man was chronic back pain. Diagnoses: Contrast-enhanced computed tomography showed a 19.1-cm sized heterogeneous enhancing mass on the right kidney and tumor thrombosis extending into inferior vena cava. Intervention: Due to the large size of the tumor and extensive tumor thrombosis, the multidisciplinary team decided to administer neoadjuvant chemotherapy and an anticoagulant. Following 12 cycles of treatment with nivolumab and cabozantinib, he underwent a right radical nephrectomy with an adrenalectomy and tumor thrombectomy. Outcomes: Treatment was successful and posttreatment he started a cancer rehabilitation program. He was followed-up as an outpatient and no longer complains of back pain. Lessons: RCC can manifest clinically as back pain, with diagnosis being difficult without appropriate imaging modalities. RCC should be included in the differential diagnosis of patients with low back pain, even at a young age.

This study presents a novel case of gastric carcinoma (GC) with diverse histological features and unique molecular alterations. A 62‑year‑old man with hematemesis was diagnosed with advanced GC and hepatic metastasis. Despite palliative gastrectomy to control bleeding, the patient succumbed within 6 months. Histological examination revealed three distinct tumour components: Gastric adenosquamous carcinoma (GASC), GC with lymphoid stroma (GCLS) and poorly differentiated adenocarcinoma (PDAD). Immunohistochemical staining, next‑generation sequencing and Epstein‑Barr virus (EBV) in situ hybridisation were performed to characterise the tumour. The GASC component revealed diffuse p40 and p63 immunoreactivity, while the GCLS and PDAD components were negative for both markers. All components harboured a missense mutation in the phosphoinositide‑3‑kinase regulatory subunit 1 gene and deletions in the ATRX and RNA binding motif protein 10 genes. Additionally, the GCLS component was EBV positive and the PDAD component demonstrated concurrent EBV infection and TP53 inactivation. The present case highlights the importance of thorough molecular and histological evaluation, as distinct molecular alterations and heterogenous EBV status in histologically diverse components may significantly influence patient prognosis and treatment strategies.

Human epidermal growth factor receptor 2 (HER2)-targeted therapies have revolutionized breast cancer treatment, necessitating standardized HER2 testing. However, current immunochemistry-based HER2 assessment faces challenges due to subjectivity and variability among observers, prompting the guidance of artificial intelligence (AI). We evaluated AI’s efficacy in HER2 status assessment and treatment response prediction, especially focusing on complete and intense circumferential HER2-positive (3+) tumor cells. An AI-powered HER2 analyzer (Lunit SCOPE HER2, Lunit Inc., Seoul, South Korea) and three pathologists independently assessed HER2 3 + tumor cell proportions from whole-slide images of 191 breast cancer cases from Kyung Hee University Hospital. Logistic regression and receiver operating characteristic (ROC) curves determined predictive accuracy. AI-detected 3 + tumor cell proportions strongly correlated with fluorescent in situ hybridization (FISH) positivity (area under ROC curve [AUC]: 0.783) and pathological complete response (pCR) rates (odds ratio [OR]: 1.003–1.052), outperforming pathologists’ assessments. Combining AI improved prediction accuracy of pathologists, with an AUC increased from 0.712–0.813 to 0.790–0.821 for predicting FISH positivity and median OR increased from 0.996–1.061 to 1.003–1.055 for predicting pCR. Overall, this preliminary study suggests that AI could enhance HER2 status determination and treatment response prediction, complementing traditional pathological evaluation of HER2 immunohistochemistry.

Immunoglobulin G4-related disease (IgG4-RD) is a novel fibroinflammatory disorder characterized by enlargement of the involved organs, elevated IgG4 levels, and abundant infiltration of IgG4-positive plasma cells. Indeed, primary colon cancers arising from IgG4-RD are rare. This case report describes a rare occurrence of simultaneous colorectal cancer and IgG4-RD in the same lesion in a 62-year-old male patient. The patient underwent a right hemicolectomy under the suspicion of primary colon cancer. The mass was grossly well-defined and yellowish tan, and the background colon was fibrotic. Microscopically, the tumor cells showed glandular differentiation characteristic of adenocarcinoma in a background of dense lymphoplasmacytic infiltration with fibrosis and obliterative phlebitis in the pericolic fat tissue. IgG4 immunohistochemical staining showed diffuse positivity in infiltrating plasma cells. The patient was administered adjuvant chemotherapy and prednisolone therapy. The patient’s serum IgG4 levels gradually decreased, and a follow-up positron emission tomography-computed tomography scan 1 year after surgery showed no evidence of local or distant recurrence of colorectal cancer. IgG4-RD occurring concurrently with primary colon adenocarcinoma has not been reported. Increased awareness of this rare coexistence can guide clinicians in navigating diagnostic complexities and selecting optimal therapeutic strategies.