Explainable DCNN Decision Framework for Breast Lesion Classification from Ultrasound Images Based on Cancer Characteristics.

In recent years, deep convolutional neural networks (DCNNs) have shown promising performance in medical image analysis, including breast lesion classification in 2D ultrasound (US) images. Despite the outstanding performance of DCNN solutions, explaining their decisions remains an open investigation. Yet, the explainability of DCNN models has become essential for healthcare systems to accept and trust the models. This paper presents a novel framework for explaining DCNN classification decisions of lesions in ultrasound images using the saliency maps linking the DCNN decisions to known cancer characteristics in the medical domain. The proposed framework consists of three main phases. First, DCNN models for classification in ultrasound images are built. Next, selected methods for visualization are applied to obtain saliency maps on the input images of the DCNN models. In the final phase, the visualization outputs and domain-known cancer characteristics are mapped. The paper then demonstrates the use of the framework for breast lesion classification from ultrasound images. We first follow the transfer learning approach and build two DCNN models. We then analyze the visualization outputs of the trained DCNN models using the EGrad-CAM and Ablation-CAM methods. We map the DCNN model decisions of benign and malignant lesions through the visualization outputs to the characteristics such as echogenicity, calcification, shape, and margin. A retrospective dataset of 1298 US images collected from different hospitals is used to evaluate the effectiveness of the framework. The test results show that these characteristics contribute differently to the benign and malignant lesions' decisions. Our study provides the foundation for other researchers to explain the DCNN classification decisions of other cancer types.

Electric-field facilitated rapid and efficient dissociation of tissues Into viable single cells.

Single-Cell Analysis is a growing field that endeavors to obtain genetic profiles of individual cells. Disruption of cell-cell junctions and digestion of extracellular matrix in tissues requires tissue-specific mechanical and chemical dissociation protocols. Here, a new approach for dissociating tissues into constituent cells is described. Placing a tissue biopsy core within a liquid-filled cavity and applying an electric field between two parallel plate electrodes facilitates rapid dissociation of complex tissues into single cells. Different solution compositions, electric field strengths, and oscillation frequencies are investigated experimentally and with COMSOL Multiphysics. The method is compared with standard chemical and mechanical approaches for tissue dissociation. Treatment of tissue samples at 100 V/cm 1 kHz facilitated dissociation of 95 ± 4% of biopsy tissue sections in as little as 5 min, threefold faster than conventional chemical-mechanical techniques. The approach affords good dissociation of tissues into single cells while preserving cell viability, morphology, and cell cycle progression, suggesting utility for sample preparation of tissue specimens for direct Single-Cell Analysis.

Optimization of a Clinically Relevant Chemical-Mechanical Tissue Dissociation Workflow for Single-Cell Analysis.

INTRODUCTION: While single-cell analysis technology has flourished, obtaining single cells from complex tissues continues to be a challenge. Current methods require multiple steps and several hours of processing. This study investigates chemical and mechanical methods for clinically relevant preparation of single-cell suspension from frozen biopsy cores of complex tissues. The developed protocol can be completed in 15 min. METHODS: Frozen bovine liver biopsy cores were normalized by weight, dimension, and calculated cellular composition. Various chemical reagents were tested for their capability to dissociate the tissue via confocal microscopy, hemocytometry and quantitative flow cytometry. Images were processed using ImageJ. Quantitative flow cytometry with gating analysis was also used for the analysis of dissociation. Physical modeling simulations were conducted in COMSOL Multiphysics. RESULTS: A rapid method for tissue dissociation was developed for single-cell analysis techniques. The results of this study show that a combination of 1% type-1 collagenase and pronase or hyaluronidase in 100 U/µL HBSS solution is the most effective at dissociating 2.5 mm thawed bovine liver biopsy cores in 15 min, with dissociation efficiency of 37-42% and viability >90% as verified using live MDA-MB-231 cancer cells. Cellular dissociation is significantly improved by adding a controlled mechanical force during the chemical process, to dissociate 93 ± 8% of the entire tissue into single cells. CONCLUSIONS: Understanding cellular dissociation in ex vivo tissues is essential to the development of clinically relevant dissociation workflows. Controlled mechanical force in combination with chemical treatment produces high quality tissue dissociation. This research is relevant to the understanding and assessment of tissue dissociation and the establishment of an automated preparatory workflow for single cell diagnostics. SUPPLEMENTARY INFORMATION: The online version of this article (10.1007/s12195-021-00667-y) contains supplementary material, which is available to authorized users.

An unusual cause of acute abdomen-Gas-forming liver abscess due to Salmonella enteritidis.

Gas-forming pyogenic liver abscess (GFPLA) is considered to be a very severe form of PLA and carries a high mortality. Klebsiella pneumoniae is the most common pathogen responsible for the disease, whereas cases where Salmonella is cited as the cause are very uncommon. We report the first case of a 53-year-old lady suffering from GFPLA due to Salmonella, who was successfully treated with surgical drainage. To the best of our knowledge, this is the first case of GFPLA caused by Salmonella enteritidis to be reported in the English literature.

Surviving emphysematous gastritis after hepatectomy.

Emphysematous gastritis is a rare variant of phlegmonous gastritis due to invasion of stomach wall by gas-forming bacteria. It is characterised by abnormal presence of gas in the stomach by imaging, in association with clinical sepsis. Patients suffering from this condition usually present with an underlying pathology. We are reporting a middle-aged Chinese male with hepatitis B virus related hepatocellular carcinoma. He underwent partial hepatectomy and was diagnosed with emphysematous gastritis 4 days after index operation. Emergency laparotomy, including upper endoscopy, was performed. He was managed with antibiotics and discharged 18 days after second operation. This paper shows a review of the literature about the disease, with particular attention to pathology, clinical features, and management.

Adjuvant therapy for the reduction of postoperative intra-abdominal adhesion formation.

BACKGROUND: To review currently available evidence on the use of adjuvant therapy to reduce the formation of postoperative intra-abdominal adhesions. METHODS: A search on Pubmed and the Cochrane library was undertaken using the keywords "abdominal", "adhesion", "postoperative", "prevention" and "reduction". Only randomised controlled trials, prospective non-randomised controlled studies and review articles published in the English language between 1990 and 2006 were included. RESULTS: Two prospective non-randomised controlled studies and 18 randomised controlled trials were included in this review. Adjuvant therapies reviewed included pharmacological agents (streptokinase, recombinant tissue plasminogen activator, vitamin E antioxidant molecules), and mechanical barriers (hyaluronic acid barriers, oxidised regenerated cellulose barriers, nanofibrous barriers and collagen foils). Hyaluronate/carboxymethylcellulose-based bioresorbable membrane (Seprafilm) appeared to be the most efficacious in reducing adhesion formation as well as decreasing the incidence of adhesion obstruction requiring reoperation in clinical studies. Drawbacks to the use of Seprafilm include high cost and complications such as haemorrhage and poor wound healing. CONCLUSIONS: Only a limited number of adjuvant treatment methods are currently available for the reduction of postoperative adhesions. Seprafilm has been proven to be the efficacious method to reduce adhesions. Investigations into the novel therapies are showing promising results in experimental studies and clinical studies before their wider application.

High sensitivity C-reactive protein: an emerging role in cardiovascular risk assessment.

Coronary heart disease (CHD) is the major cause of death in the developed world and screening for conventional cardiovascular risk factors fails to identify more than 50% of the individuals who will present with acute coronary syndromes. Chronic inflammation appears to play a significant role in the initiation and development of atherosclerosis. Recent investigations have shown an association between inflammatory markers such as C-reactive protein (CRP) and CHD. These markers have proven useful as prognostic indicators in acute coronary syndromes and in predicting future coronary events in apparently healthy men and women. The availability of high sensitivity CRP (hs-CRP) assays has been crucial in exploring the role of this acute phase reactant in primary prevention settings. In this review, we discuss the evidence associating these inflammatory markers, especially CRP, with the pathogenesis of atherosclerosis and acute coronary syndromes, and we address the mechanism of risk as well as the clinical utility of this marker.