Future of prostate imaging: Artificial intelligence in assessing prostatic magnetic resonance imaging

Background and Objectives: Breast cancer (BC) is a global health concern for women; the disease contributes to significant morbidity and mortality. A key element in the diagnosis of BC involves the histopathological diagnosis, which determines patient management and therapy. However, BC is a multifaceted disease, limiting access to early diagnosis and, therefore, treatment. Artificial intelligence (AI) is transforming diagnostics in the medical field, especially in the detection of BC. Due to the increased availability of digital slides, it has facilitated the effective integration of AI in breast cancer diagnosis. Diagnosis poses a great challenge, even for experienced pathologists, due to the heterogeneity of this malignancy. Analysing microscopic slides by pathologists requires a considerable amount of time. Implementation of AI into routine workflows holds potential to improve diagnostic sensitivity and inter-observer concordance, and to increase efficiency by reducing the review time, thereby helping to alleviate the burden of diagnosing BC. Previous studies mainly address imaging modalities or oncology broadly, while a few specifically concentrates on the histopathological aspect of breast cancer. This review aims to explore the novel synthesis of AI advancements in digital pathology, including tumour classification, grading, lymph node staging, and biomarker evaluation, and discuss their potential incorporation into clinical workflows. We will also discuss the current barriers and prospects for future advancements. Materials and Methods: A literature search was conducted in PubMed and Google Scholar using the mentioned keywords. Articles published in English until July 2025 were reviewed and synthesised narratively. Results: Recent studies demonstrate that AI models such as convolutional neural networks (CNNs), YOLO, and RetinaNet achieve high accuracy in tumour detection, histological grading, lymph node metastasis localisation, and biomarker analysis. The reported performance values range from 75% to over 95% accuracy across various tasks, with gains in diagnostic sensitivity and inter-observer concordance, and reduced review time in assisted workflows. However, certain limitations, such as data variability, external validation in clinical practice, and ethical concerns, restrict the growth and optimal performance of AI and its clinical applicability. Conclusions: The future for AI looks promising, as it is rapidly evolving. By analysing evidence across multiple domains, this review evaluates both opportunities and persisting barriers, offering practical overviews for future clinical transition. AI cannot replace pathologists; however, it has the capabilities to enhance diagnostic precision, efficiency, and ultimately patient outcomes. It is only a matter of time before AI is adopted into healthcare.

Introduction: Low anterior resection (LAR) is a standard surgical procedure for distal rectal carcinoma that allows creation of a colorectal anastomosis, with anal sphincter preservation and permanent colostomy avoidance. Anastomotic leakage (AL) is a potential complication of LAR present in 3% to 20% of cases leading to a significant increase in postoperative morbidity. AL represents a communication between the intra luminal and extra luminal compartments caused by a violation of the integrity of the intestinal wall. The risk factors of this procedure have been discussed and still remain a controversial issue. Prevention is the best management. Patients with predisposing factors should be paid special attention. Aim: Our objective was to identify and analyze the risk factors of anastomotic leakage after low anterior resection of rectal carcinoma. Patients and methods: This study included all patients who underwent low anterior resection for rectal cancer at the Department of Surgery of University Hospital Kaspela between 2011 and 2016. Results: Low anterior resections were performed in 141 patients during the study period. Due to a positive air leak test on 16 patients, a protective ileostomy was created and these patients were eliminated from the study. The sex distribution of the remaining 125 patients was 69 men (55.2%) and 56 women (44.8%). The height of the anastomosis from the dentate line was 3.0 cm on an average (range 2.5 to 4 cm). Conclusion: Anastomotic leakage remains the most feared and serious complication after low anterior resection surgery. The evidence suggests that the main risk factors for anastomotic leakage at low anterior resection are the height of the anastomosis and the high ASA score.

Introduction. Pancreatic ductal adenocarcinoma (PDA) is associated with poor prognosis and 98% loss-of-life expectancy. 80% of patients with PDA are unfit for radical surgery. In those cases, emphasis is set on management of cancer-related symptoms, among which obstructive jaundice is most common. Endoscopic ultrasound-guided biliary drainage (EUS-BD) emerges as a valid alternative to the well-accepted methods for treatment of biliary obstruction. Patient Selection. Five consecutive patients with unresectable pancreatic malignancy, were subjected to EUS-BD, particularly EUS-guided choledochoduodenostomy (EUS-CDS). Ethics. Oral and written informed consent was obtained in all cases prior procedure. Technique. EUS-guided puncture of the common bile duct was performed, followed by advancement of a guidewire to the intrahepatic bile ducts. After dilation of the fistulous tract with a cystotome, a fully covered self-expandable metal stent was inserted below the hepatic confluence and extending at least 3 cm in the duodenum. Technical and clinical success was achieved in four patients without adverse events. In one patient procedure failed due to dislocation of the guidewire, with consequent biliary leakage requiring urgent surgery. Recovery was uneventful with no further clinical sequelae and there was no mortality associated with procedure. Discussion. Introduced in 2001, EUS-guided biliary drainage has become an accepted option for treatment of obstructive jaundice. According to recent guidelines published by European Society of Gastrointestinal Endoscopy (ESGE) in 2022, EUS-CDS is a preferred modality to percutaneous transhepatic biliary drainage (PTBD) and surgery in patients with failed ERCP, with comparable efficiency and better safety profile, which is supported by our experience with the procedure. Conclusions. Our case series suggests that EUS-CDS is an excellent option for palliative management of malignant distal biliary obstruction, emphasizes on the importance of adequate technique and experience for the technical success, and urges the need for future research on establishing the best choice for guidewire and dilation device.

Portal hypertension (PH) and esophageal varices (EVs) are a matter of extensive research. According to current Baveno VII guidelines, in patients with compensated advanced chronic liver disease (cACLD), liver stiffness measurement (LSM) < 15 kPa and PLT count > 150 × 10⁹/L, upper endoscopy (UE) is not mandatory, and the emphasis should be set on non-invasive methods for evaluation of clinically significant portal hypertension (CSPH). The aim of this study is to establish whether liver stiffness (LS) measured by 2D-SWE could be used as a predictor for the presence and severity of EVs in cirrhotic patients. In total, 86 patients of whom 32 with compensated liver cirrhosis (cLC) and 54 with decompensated liver cirrhosis (dLC) were examined in the Gastroenterology clinic of University hospital “Kaspela”, Plovdiv, Bulgaria. Each patient underwent LS assessment by 2D-SWE and EVs grading by UE. EVs were detected in 47 (54.7%) patients, 23 (49%) of them were stage 4-high-risk EVs (HREV). The cut-off value for LS that differentiates HREV from the rest was set at 2.49 m/s with 100% sensitivity and 100% specificity (AUC 1.000, CI 0.925). Conclusions: 2D-SWE can be used as a non-invasive method in the assessment of only high-grade esophageal varices. For the other grades, upper endoscopy remains the method of choice.

Introduction: Papillary thyroid cancer is the most common thyroid malignancy. Lymph nodes involvement is common in differentiated thyroid cancer, and cervical lymph node micrometastases are observed in up to 85% of patients with papillary thyroid cancer during surgery. While the therapeutic central lymph node dissection has been accepted, the debate on the prophylactic in differentiated thyroid carcinoma (DTC) continues. Aim: To evaluate the benefits and risk of prophylactic central lymph node dissection in differentiated thyroid cancer. Materials and methods: Between January 2014 and December 2018, 223 total thyroidectomies due to papillary thyroid cancer were performed in the Kaspela University Hospital in Plovdiv. The patients were allocated into two groups: group A consisting of 36 patients with total thyroidectomy alone, and group B - 178 patients with total thyroidectomy and prophylactic central lymph node dissection. Results: In 36 (21.6%) patients, we found metastases only in ipsilateral side. In 24 (13.4%) of them we found metastatic spread in both ipsilateral and contralateral lymph nodes. In 7 (3.9%) patients, the metastasis was found only in the contralateral nodes. A pre-laryngeal lymph node was found and removed in 79 patients. Metastases were found in 12 of these 79 nodes. Analysis of complications showed no significant differences in its rate in patients with TT+ PCLND vs. patients with TT alone. Conclusions: The present study suggests that the realization of total thyroidectomy with prophylactic central lymph node dissection in papillary thyroid cancer patients has neither substantial advantages nor significant complications for the short period of observation.