Imaging findings of prostate tuberculosis by transrectal contrast-enhanced ultrasound and comparison with 2D ultrasound and pathology

Objectives: This study aimed to investigate the contrast-enhanced ultrasound (CEUS) appearances of prostate tuberculosis (PTB) and its correlation with histopathology. Methods: Clinical, transrectal ultrasonography (TRUS) and CEUS data of 12 PTB patients confirmed by pathology were retrospectively analyzed, and compared to the pathological findings to identify the pathological structures corresponding to different image enhancement areas. Results: No specific characteristics could be found for the clinical appearances. Enlarged gland, hypoechoic lesions and calcification due to PTB could be found by TRUS, which were also non-specific. CEUS showed hypo- or non-enhanced lesions with varying size, which were related to different pathological stages of PTB. The incidence rate of non-enhanced lesions was 83.3%. The detection rate of suspected lesion by CEUS was significantly higher than that by TRUS (χ2 = 8.000, p = 0.005). Histopathology showed that the hypoenhanced area consisted of tuberculous granulomas, caseous necrosis and incomplete destruction of the glands, while the non-enhanced area consisted of caseous or liquified necrosis. Conclusion: CEUS could improve the detection rate of PTB lesions, and the diversity of its manifestations was related to different pathological structures. An enlarged, soft gland with non-enhanced on CEUS may provide valuable information for the diagnosis of PTB, but it is not a substitute for biopsy due to the diversity of CEUS findings. Advances in knowledge: When the lesions of prostate gland are unclear in TRUS examination, CEUS is an ideal option for the detection of lesions, which is conducive to targeted guidance of biopsy areas.

Implementation of artificial intelligence algorithms for melanoma screening in a primary care setting

Skin cancer is currently the most common type of cancer among Caucasians. The increase in life expectancy, along with new diagnostic tools and treatments for skin cancer, has resulted in unprecedented changes in patient care and has generated a great burden on healthcare systems. Early detection of skin tumors is expected to reduce this burden. Artificial intelligence (AI) algorithms that support skin cancer diagnoses have been shown to perform at least as well as dermatologists’ diagnoses. Recognizing the need for clinically and economically efficient means of diagnosing skin cancers at early stages in the primary care attention, we developed an efficient computer-aided diagnosis (CAD) system to be used by primary care physicians (PCP). Additionally, we developed a smartphone application with a protocol for data acquisition (i.e., photographs, demographic data and short clinical histories) and AI algorithms for clinical and dermoscopic image classification. For each lesion analyzed, a report is generated, showing the image of the suspected lesion and its respective Heat Map; the predicted probability of the suspected lesion being melanoma or malignant; the probable diagnosis based on that probability; and a suggestion on how the lesion should be managed. The accuracy of the dermoscopy model for melanoma was 89.3%, and for the clinical model, 84.7% with 0.91 and 0.89 sensitivity and 0.89 and 0.83 specificity, respectively. Both models achieved an area under the curve (AUC) above 0.9. Our CAD system can screen skin cancers to guide lesion management by PCPs, especially in the contexts where the access to the dermatologist can be difficult or time consuming. Its use can enable risk stratification of lesions and/or patients and dramatically improve timely access to specialist care for those requiring urgent attention.

Computer-Aided Decision-Making System for Endometrial Atypical Hyperplasia based on Multimodal & Multi-Instance Deep Convolution Networks

The pathological diagnosis is the gold standard for neoplasms and their precursors, which is highly relevant to the treatment planning and the prognostic analysis. Currently, deep learning networks have been used for the pathological computer-assisted diagnosis and treatment decision-makings. However, due to extremely large size of the whole slide images (WSIs) of pathological slides, the prevailing deep learning models are un-applicable directly in the WSIs analysis. Moreover, the precise exclusion of the blank regions and interfere regions, as well as the manual annotation of various lesioned and normal regions in super large WSIs are infeasible and unavailable in clinical practice. To address aforementioned problems, we develop an computer-aided decision-making system based on multimodal and multi-instance deep convolution networks (CNN) to assist in the diagnosis and treatment of endometrial atypical hyperplasia (AH)/ endometrial intraepithelial hyperplasia (EIH). Firstly, we set up the frame-work of computer-aided decision-making system based on the WSIs image patterns of AH/EIH, and then transfer the large-scale WSI analysis to the small-scale analysis of multiple suspected lesion regions which can be accomplished the major computer vision models, and eventually the results of prognostic analysis for multiple small-scale suspected lesion regions are summarized to obtain the prognostic results of WSIs by the decision supporting algorithm based on the cognition intelligence. We validate the method via experimental analysis of 102 endometrial atypical hyperplasia patients at the West China Second University Hospital of Sichuan University. The performance achieved for endometrial AH/EIH prognostic analysis includes accuracy (85.3%), precision (84.6%), recall (86.3%). Meanwhile, the method has superior performance to prognostic judgment of a single pathologist as well as approximates to analysis results determined by three pathologists according to the majority voting method.

Analysis of frozen section in correlation with surgical pathology diagnosis

Background: Frozen section (FS) is a rapid diagnostic procedure performed on tissues obtained intraoperatively. This method serves useful purposes, such as determining the malignancy or benignancy of a suspected lesion, determining the adequacy of a biopsy of a suspected lesion, confirming the presence or absence of metastasis, and identifying small structures. But it bears many disadvantages and limitations, the most of which is the danger of incorrect diagnosis. Therefore, it is critical to determine efficiency of frozen section performance periodically. This study was performed to determine accuracy of frozen section by correlating the intra-operative frozen section diagnosis with final diagnosis on permanent sections.Methods: In this retrospective study, authors compared the results of frozen section with their final permanent section diagnosis in Government Medical College and Hospital, Aurangabad, Maharashtra, India during January 2017 to December 2018.Results: Study comprises 83 patients, of which 73 were female and 10 were male. Out of 83 cases, the diagnosis of 76 cases was concordant with conventional histopathology diagnosis while seven were discordant. This gave overall accuracy rate of 91.57% and discordant rate of 8.43%. The overall sensitivity was 85.71% and specificity was 97.92%. The positive predictive and negative predictive value was 96.77% and 90.38% respectively.Conclusions: The accuracy, sensitivity, specificity of frozen section diagnosis in this study are comparable with most international quality control statistics for frozen sections. The results suggest that the correlation of intra-operative frozen section diagnosis with the final histopathological diagnosis on permanent sections forms an integral part of quality assurance activities in the surgical pathology laboratory and specific measures should be taken to reduce the number of discrepancies.

Colposcopic evaluation of unhealthy cervix and it’s correlation with Papanicolau smear in cervical cancer screening

Background: In present study colposcopic evaluation of unhealthy cervix was donr and it’s correlation with Papanicolau smear in screening of Cancer cervix. Objective of present study was to critically evaluate the sensitivity and specificity of PAP smear with that of Colposcopy in screening of Cancer Cervix in women with unhealthy cervix.Methods: 100 women with clinically unhealthy cervix on naked eye examination and / or abnormal symptoms attending Gynaecology Out patient department in 2 years period were subjected to PAP smear, Colposcopy, biopsies under Colposcopic guidance and findings correlated with Histopatholgy at Govt. Medical college, Aurangabad, Maharashtra. India. The sensitivity and specificity of PAP smear with that of Colposcopy in screening of Cancer Cervix was evaluated.Results: Both PAP smear and Colposcopy can be reliably used to screen women with premalignant lesions of Cancer cervix.Conclusions: Colposcopy is a better tool for diagnosis of precursors of Cancer Cervix than PAP Smear and Histopathology of suspected lesion remains the gold standard for final diagnosis.

A Method for Extracting Suspected Parotid Lesions in CT Images using Feature-based Segmentation and Active Contours based on Stationary Wavelet Transform

Automatic suspected lesion extraction is an important application in computer-aided diagnosis (CAD). In this paper, we propose a method to automatically extract the suspected parotid regions for clinical evaluation in head and neck CT images. The suspected lesion tissues in low contrast tissue regions can be localized with feature-based segmentation (FBS) based on local texture features, and can be delineated with accuracy by modified active contour models (ACM). At first, stationary wavelet transform (SWT) is introduced. The derived wavelet coefficients are applied to derive the local features for FBS, and to generate enhanced energy maps for ACM computation. Geometric shape features (GSFs) are proposed to analyze each soft tissue region segmented by FBS; the regions with higher similarity GSFs with the lesions are extracted and the information is also applied as the initial conditions for fine delineation computation. Consequently, the suspected lesions can be automatically localized and accurately delineated for aiding clinical diagnosis. The performance of the proposed method is evaluated by comparing with the results outlined by clinical experts. The experiments on 20 pathological CT data sets show that the true-positive (TP) rate on recognizing parotid lesions is about 94%, and the dimension accuracy of delineation results can also approach over 93%.