Current Medical Imaging - Volume 19, Issue 3, 2023

Background: Skin disease image analysis has drawn extensive attention from researchers, which can help doctors efficiently diagnose skin disease from medical images. Existing reviews have focused only on the specific task of skin disease diagnosis based on a single medical image type. Discussion: This paper presents the latest and comprehensive review of image analysis methods in skin diseases, and summarizes over 350 contributions to the field, most of which appeared in the last three years. We first sort out representative publicly available skin datasets and summarize their characteristics. Thereafter, aiming at the typical problems exposed by datasets, we organize the image preprocessing and data enhancement part. Further, we review the single tasks of skin disease image analysis in the literature, such as classification, detection or segmentation, and analyze the improvement direction of their corresponding methods. Additionally, popular multi-task models based on structure and loss function are also investigated. Conclusions: Challenges involved from the aspects of the dataset and model structure have been discussed.

The diagnosis of tumors in the initial stage plays a crucial role in improving the clinical outcomes of a patient. Evaluation of brain tumors from many MRI images generated regularly in a clinical environment is a complex and time-consuming process. Therefore,there comes a need for an efficient and accurate model for the early detection of tumors. This paper revolves around the current strategies used for brain tumor segmentation and classification from MRI images of the brain. This approach also tries to pave the way for the significance of their performance measure and quantitative evaluation of forefront strategies. This state of the art clearly describes the importance of several brain image segmentation and classification methodsduring the past 13 years of publication by various researchers. In this instance, new calculations are being made for potential clients to analyze the concerned area of research. This review acknowledges the key accomplishments expressed in the diagnostic measures and their success indicators of qualitative and quantitative measurement. This research study also explores the key outcomes and reasons for finding the lessons learned.

Objectives: This study aims to investigate the usefulness of diffusion-weighted imaging (DWI) and arterial spin labeling (ASL) for predicting final infarct volume in patients with acute atherothrombotic subtype cerebral infarction (AT-type stroke). Methods: The data of 77 patients with AT-type stroke were retrospectively analyzed. ASL and DWI values of minimum apparent diffusion coefficient (min ADC), mean ADC (mean ADC), minimum cerebral blood flow (min CBF), and mean CBF (mean CBF) of the infarction lesions were measured. Changes in cerebral infarction volume (ΔVolume) were determined by DWI reexamination on the 7th day after onset. Correlations of ADC and CBF with Δ Volume were analyzed. Receiver operating characteristic (ROC) curve analysis was used to determine the usefulness of ADC and CBF values for predicting final infarct volume. Results: There was a significant difference in the distribution of the ΔVolume in AT-type stroke (P<0.0001). The ADC and min CBF values were negatively correlated with the infarct ΔVolume (P<0.05); mean CBF and ΔCBF were not correlated with ΔVolume. When min ADC was ≤0.303 × 10^-3 mm²/s, min CBF 1.5 ≤2.415 mL/100 g/min, or min CBF2.5 ≤4.25 mL/100 g/min, ΔVolume was likely to be large. The ROC curve showed the highest predictive value for min ADC and min CBF. Conclusion: Distinctive patterns of quantitative ADC and CBF can be used as a simple and rapid method for predicting change in infarction volume in AT-type stroke.

Objectives: The study aims to evaluate the value of the mandible transection head-side shifting method (MTHSM) by 2-dimensional sonography in the screening of fetal cleft lip and palate (CLP) during the nuchal translucency scans. Methods: A total of 7,336 fetuses enrolled for first-trimester aneuploidy screening were included in this prospective study. A sequential scanning approach from the mandible transection toward the head was used for the assessment of the palate in the midsagittal, axial, and coronal sections. Observe the continuity of the palatal line, upper alveolar ridge, and primary palate. All fetuses were followed by second-trimester scans and postnatal evaluation. Results: A total of 18 cases of CLP were identified in the first trimester based on this method. Out of 18, 9 (50.0%) were unilateral CLP, 4 (22.2%) were bilateral CLP, and 5 (27.8%) were median CLP. There were no false-positive results found. Three were missed but confirmed in the second-trimester anomaly scan, including 2 cases of isolated cleft palate (CP) and one of isolated cleft lip (CL). Firsttrimester diagnosis of CLP using MTHSM had a sensitivity of 85.7%, a specificity of 100%, a positive predictive value of 100%, and a negative predictive value of 99.9%. Conclusion: The mandible transection head-side shifting method is feasible in assessing CLP at the time of routine first-trimester sonographic screening.

Background: Ultrasound elastography (US-E) has been shown superior to the conventional US in diagnosing benign and malignant breast lesions. In contrast, the role of US-E in the differentiation of breast invasive ductal carcinoma (IDC) and ductal carcinoma in situ (DCIS) has been poorly described. Objective: This study was designed to examine the diagnostic value of US-E in the differentiation of IDC and DCIS. Methods: Medical records of all patients who underwent preoperative US-E evaluation and were diagnosed with IDC or DCIS at our hospital from April-December 2019 were retrieved and analyzed. Those who had prior surgical treatment, chemotherapy or radiotherapy were excluded. Results: Twenty women with DCIS and 111 women with IDC were included in this study. There were no significant differences in age, maximum lesion diameter and tumor volume between the two groups. While shear wave velocity (SWV) inside the lesion and in the surrounding tissue, strain ratio and tumor area ratio were not substantially different between the two groups, SWV at the edge of the lesion was significantly higher in IDC cases, which had an AUC value of 0.66 with a sensitivity of 65.8% and a specificity of 60.0% for the differential diagnosis of IDC and DCIS. Conclusion: Edge SWV is significantly higher in IDC than that in DCIS, which had a moderate diagnostic value for the differentiation of IDC and DCIS, similar to the performance of diffusion-weighted magnetic resonance imaging as reported in the literature. In terms of cost-effectiveness, US-E could be very useful while waiting for further evaluations to determine whether US-E combined with other diagnostic modalities improves the diagnostic performance.

Objective: To develop a computerized diagnostic model to characterize the ovarian cyst at its early stage in order to avoid unnecessary biopsy and patient anxiety. Background: The main cause of mortality and infertility in women is ovarian cancer. It is very difficult to diagnose ovarian cancer using ultrasonography as benign and malignant ovarian masses or cysts exhibit similar characteristics. Early prediction and characterization of ovarian masses will reduce the unwanted growth of the ovarian mass. Materials and Methods: Transvaginal 2D B mode ovarian mass ultrasound images were preprocessed initially to enhance the image quality. And then, the region of interest (ROI) in this case ovarian cyst was segmented. Finally, Local Binary Pattern (LBP) textural features were extracted. A Support Vector Machine was trained to classify the ovarian cyst or mass as benign or malignant. Results: The performance of the SVM improved with an average accuracy of 92% when the textural features were extracted from the Original Gray Value-based LBP (OGV-LBP) image than the histogram- based LBP. Conclusion: The SVM can classify the transvaginal 2D B mode ovarian cyst ultrasound images into benign and malignant effectively when the textural features from the original gray value-based LBP extracted were considered.