Diagnosis of focal liver lesions from ultrasound images using a pretrained residual neural network.

OBJECTIVE: This study aims to develop a ResNet50-based deep learning model for focal liver lesion (FLL) classification in ultrasound images, comparing its performance with other models and prior research. METHODOLOGY: We retrospectively collected 581 ultrasound images from the Chulabhorn Hospital's HCC surveillance and screening project (2010-2018). The dataset comprised five classes: non-FLL, hepatic cyst (Cyst), hemangioma (HMG), focal fatty sparing (FFS), and hepatocellular carcinoma (HCC). We conducted 5-fold cross-validation after random dataset partitioning, enhancing training data with data augmentation. Our models used modified pre-trained ResNet50, GGN, ResNet18, and VGG16 architectures. Model performance, assessed via confusion matrices for sensitivity, specificity, and accuracy, was compared across models and with prior studies. RESULTS: ResNet50 outperformed other models, achieving a 5-fold cross-validation accuracy of 87 ± 2.2%. While VGG16 showed similar performance, it exhibited higher uncertainty. In the testing phase, the pretrained ResNet50 excelled in classifying non-FLL, cysts, and FFS. To compare with other research, ResNet50 surpassed the prior methods like two-layered feed-forward neural networks (FFNN) and CNN+ReLU in FLL diagnosis. CONCLUSION: ResNet50 exhibited good performance in FLL diagnosis, especially for HCC classification, suggesting its potential for developing computer-aided FLL diagnosis. However, further refinement is required for HCC and HMG classification in future studies.

Ultrasound surveillance for cholangiocarcinoma in an endemic area: A prove of survival benefits.

BACKGROUND AND AIM: Cholangiocarcinoma (CCA) is an aggressive malignancy with rapid progression and poor prognosis. Abdominal ultrasound surveillance may detect early-stage malignancy and improve surgical outcome. However, little data exist on the benefits of abdominal ultrasound surveillance in populations at high risk for CCA development in an endemic area. This study compared survival outcomes of CCA patients recruited through abdominal ultrasound surveillance program and those presented to the hospital independent of surveillance. METHODS: The surveillance population-based cohort was 4225 villagers in Northern Thailand, aged 30-60 years, who consented to a 5-year abdominal ultrasound surveillance program, which included interval ultrasound examinations every 6 months. The non-surveillance cohort was hospital-based CCA patients diagnosed during April 2007 to November 2015. Numbers of operable tumors, percentages of R0 resection, and survival analyses were compared between the two cohorts. RESULTS: There were 48 and 192 CCA patients in the surveillance and the non-surveillance cohorts, respectively. Of these, 37/48 (77.1%) and 22/192 (11.5%) were in an operable stage and R0 resections performed in 36/48 (97.3%) and 14/192 (63.6%), respectively. The median survival in each group was 31.8 and 6.7 months, respectively (with correction of lead time bias) (P < 0.0001). By multivariate analysis, abdominal ultrasound surveillance (hazard ratio [HR] = 0.41; P = 0.012), operable stage (HR = 0.11; P < 0.001), and serum albumin ≥ 3.5 g/dL (HR = 0.42; P < 0.001) were significantly associated with decreased mortality, whereas size of CCA (HR = 1.11; P < 0.001), serum alanine aminotransferase > 40 IU/L (HR = 1.71; P = 0.017), and tumor recurrence (HR = 4.86; P = 0.017) were associated with increased mortality. CONCLUSION: Abdominal ultrasound surveillance provided survival benefits and should be considered in areas highly endemic for CCA to reduce mortality.