Digital breast tomosynthesis (DBT) is a fairly recent breast imaging technique invented to overcome the challenges of overlapping breast tissue. Ultrasonography (USG) was used as a complementary tool to DBT for the purpose of this study. Nonetheless, breast magnetic resonance imaging (MRI) remains the most sensitive tool to detect breast lesion. The purpose of this study was to evaluate diagnostic performance of DBT, with and without USG, versus breast MRI in correlation to histopathological examination (HPE). This was a retrospective study in a university hospital over a duration of 24 months. Findings were acquired from a formal report and were correlated with HPE. The sensitivity of DBT with or without USG was lower than MRI. However, the accuracy, specificity and PPV were raised with the aid of USG to equivalent or better than MRI. These three modalities showed statistically significant in correlation with HPE (p < 0.005, chi-squared). Generally, DBT alone has lower sensitivity as compared to MRI. However, it is reassuring that DBT + USG could significantly improve diagnostic performance to that comparable to MRI. In conclusion, results of this study are vital to centers which do not have MRI, as complementary ultrasound can accentuate diagnostic performance of DBT.
A 57-year-old Malay nullipara initially presented with a right breast lump that was increasing in size but defaulted follow-up. Two years later, she developed a contralateral breast lump. She only returned to the hospital when the right breast lump had become painful, 4 years from its onset. The biopsy of the right breast lump was a phylloides tumor and that of the left breast lump was a carcinoma. She had bilateral palpable axillary lymph nodes. She underwent bilateral mastectomy and axillary dissection. The pathology report confirmed the right breast lesion to be a malignant phylloides and the left breast lesion to be a carcinoma (pT3N2). She declined adjuvant treatment. A year after the surgical operation of the metachronous lesions, she had a right chest wall recurrence with widespread pulmonary metastases. She was given palliative chemotherapy but succumbed several months later.
Artificial intelligence (AI) use in diabetes care is increasingly being explored to personalise care for people with diabetes and adapt treatments for complex presentations. However, the rapid advancement of AI also introduces challenges such as potential biases, ethical considerations, and implementation challenges in ensuring that its deployment is equitable. Ensuring inclusive and ethical developments of AI technology can empower both health-care providers and people with diabetes in managing the condition. In this Review, we explore and summarise the current and future prospects of AI across the diabetes care continuum, from enhancing screening and diagnosis to optimising treatment and predicting and managing complications.
Primary diabetes care and diabetic retinopathy (DR) screening persist as major public health challenges due to a shortage of trained primary care physicians (PCPs), particularly in low-resource settings. Here, to bridge the gaps, we developed an integrated image-language system (DeepDR-LLM), combining a large language model (LLM module) and image-based deep learning (DeepDR-Transformer), to provide individualized diabetes management recommendations to PCPs. In a retrospective evaluation, the LLM module demonstrated comparable performance to PCPs and endocrinology residents when tested in English and outperformed PCPs and had comparable performance to endocrinology residents in Chinese. For identifying referable DR, the average PCP's accuracy was 81.0% unassisted and 92.3% assisted by DeepDR-Transformer. Furthermore, we performed a single-center real-world prospective study, deploying DeepDR-LLM. We compared diabetes management adherence of patients under the unassisted PCP arm (n = 397) with those under the PCP+DeepDR-LLM arm (n = 372). Patients with newly diagnosed diabetes in the PCP+DeepDR-LLM arm showed better self-management behaviors throughout follow-up (P