Multi-scale multi-attention network for diabetic retinopathy grading.

Objective.Diabetic retinopathy (DR) grading plays an important role in clinical diagnosis. However, automatic grading of DR is challenging due to the presence of intra-class variation and small lesions. On the one hand, deep features learned by convolutional neural networks often lose valid information about these small lesions. On the other hand, the great variability of lesion features, including differences in type and quantity, can exhibit considerable divergence even among fundus images of the same grade. To address these issues, we propose a novel multi-scale multi-attention network (MMNet).Approach.Firstly, to focus on different lesion features of fundus images, we propose a lesion attention module, which aims to encode multiple different lesion attention feature maps by combining channel attention and spatial attention, thus extracting global feature information and preserving diverse lesion features. Secondly, we propose a multi-scale feature fusion module to learn more feature information for small lesion regions, which combines complementary relationships between different convolutional layers to capture more detailed feature information. Furthermore, we introduce a Cross-layer Consistency Constraint Loss to overcome semantic differences between multi-scale features.Main results.The proposed MMNet obtains a high accuracy of 86.4% and a high kappa score of 88.4% for multi-class DR grading tasks on the EyePACS dataset, while 98.6% AUC, 95.3% accuracy, 92.7% recall, 95.0% precision, and 93.3% F1-score for referral and non-referral classification on the Messidor-1 dataset. Extensive experiments on two challenging benchmarks demonstrate that our MMNet achieves significant improvements and outperforms other state-of-the-art DR grading methods.Significance.MMNet has improved the diagnostic efficiency and accuracy of diabetes retinopathy and promoted the application of computer-aided medical diagnosis in DR screening.

Deep Learning Methods in Medical Image-Based Hepatocellular Carcinoma Diagnosis: A Systematic Review and Meta-Analysis.

(1) Background: The aim of our research was to systematically review papers specifically focused on the hepatocellular carcinoma (HCC) diagnostic performance of DL methods based on medical images. (2) Materials: To identify related studies, a comprehensive search was conducted in prominent databases, including Embase, IEEE, PubMed, Web of Science, and the Cochrane Library. The search was limited to studies published before 3 July 2023. The inclusion criteria consisted of studies that either developed or utilized DL methods to diagnose HCC using medical images. To extract data, binary information on diagnostic accuracy was collected to determine the outcomes of interest, namely, the sensitivity, specificity, and area under the curve (AUC). (3) Results: Among the forty-eight initially identified eligible studies, thirty studies were included in the meta-analysis. The pooled sensitivity was 89% (95% CI: 87-91), the specificity was 90% (95% CI: 87-92), and the AUC was 0.95 (95% CI: 0.93-0.97). Analyses of subgroups based on medical image methods (contrast-enhanced and non-contrast-enhanced images), imaging modalities (ultrasound, magnetic resonance imaging, and computed tomography), and comparisons between DL methods and clinicians consistently showed the acceptable diagnostic performance of DL models. The publication bias and high heterogeneity observed between studies and subgroups can potentially result in an overestimation of the diagnostic accuracy of DL methods in medical imaging. (4) Conclusions: To improve future studies, it would be advantageous to establish more rigorous reporting standards that specifically address the challenges associated with DL research in this particular field.

The multi-level and multi-dimensional quantum wavelet packet transforms.

The classical wavelet packet transform has been widely applied in the information processing field. It implies that the quantum wavelet packet transform (QWPT) can play an important role in quantum information processing. In this paper, we design quantum circuits of a generalized tensor product (GTP) and a perfect shuffle permutation (PSP). Next, we propose multi-level and multi-dimensional (1D, 2D and 3D) QWPTs, including a Haar QWPT (HQWPT), a D4 QWPT (DQWPT) based on the periodization extension and their inverse transforms for the first time, and prove the correctness based on the GTP and PSP. Furthermore, we analyze the quantum costs and the time complexities of our proposed QWPTs and obtain precise results. The time complexities of HQWPTs is at most 6 on 2n elements, which illustrates high-efficiency of the proposed QWPTs. Simulation experiments demonstrate that the proposed QWPTs are correct and effective.

Development of new rabbit monoclonal antibody to progesterone receptor (Clone SP2): no heat pretreatment but effective for paraffin section immunohistochemistry.

Evaluation of estrogen and progesterone receptor (ER, PgR) status in breast cancer is widely used for the prediction of the response to endocrine therapy and as a biologic parameter closely related to disease prognosis. The IHC method is considered to be a specific, sensitive, and economical method for determining ER and PgR status. The authors developed the first rabbit anti-PgR mAb (clone SP2) used in IHC on formalin-fixed, paraffin-embedded tissue sections from breast carcinomas. This new antibody, compared with currently available anti-PgR antibodies, has important advantages, including its reactivity even without heat-based antigen retrieval of fixed-embedded tissue sections in IHC and the predominance of nuclear immunostaining with only very low cytoplasmic signal. A comparative study of IHC on 107 histologic specimens from breast cancer cases showed that SP2 yields the same results as the wellknown mouse mAb to PgR (clone 1A6). The antibody affinity of SP2 is 12 times higher than that of 1A6. Thus, SP2 may prove of great value in the assessment of PgR status in human breast cancer.

Development of new rabbit monoclonal antibody to estrogen receptor: immunohistochemical assessment on formalin-fixed, paraffin-embedded tissue sections.

Evaluation of estrogen and progesterone receptors in breast cancer is widely used for the prediction of the response to endocrine therapy and as a biologic parameter closely related to disease prognosis. Immunohistochemistry is considered a specific, sensitive, and economic method for the determination of estrogen receptor/progesterone receptor status. The authors developed the first rabbit antiestrogen receptor monoclonal antibody (clone SP1) used in immunohistochemistry on formalin-fixed, paraffin-embedded tissue sections especially from breast carcinomas. This new antibody, compared with currently available antiestrogen receptor antibodies, has important advantages, including its reactivity even without heat-based antigen retrieval of fixed, embedded tissue sections in immunohistochemistry, and the predominance of nuclear immunostaining with only a very low cytoplasmic signal. A comparative study of immunohistochemistry on 61 histologic specimens from breast cancer cases showed that SP1 yields the same results as the well-known, standardized mouse monoclonal antibody to estrogen receptor (clone 1D5). Antibody affinity of SP1 is 8 times higher than that of 1D5. Thus, SP1 may prove of great value in the assessment of estrogen receptor status in human breast cancer.

Molecular mechanism of metal-independent decomposition of lipid hydroperoxide 13-HPODE by halogenated quinoid carcinogens.

Halogenated quinones are a class of carcinogenic intermediates and newly identified chlorination disinfection by-products in drinking water. 13-Hydroperoxy-9,11-octadecadienoic acid (13-HPODE) is the most extensively studied endogenous lipid hydroperoxide. Although it is well known that the decomposition of 13-HPODE can be catalyzed by transition metal ions, it is not clear whether halogenated quinones could enhance its decomposition independent of metal ions and, if so, what the unique characteristics and similarities are. Here we show that 2,5-dichloro-1,4-benzoquinone (DCBQ) could markedly enhance the decomposition of 13-HPODE and formation of reactive lipid alkyl radicals such as pentyl and 7-carboxyheptyl radicals, and the genotoxic 4-hydroxy-2-nonenal (HNE), through the complementary application of ESR spin trapping, HPLC-MS, and GC-MS methods. Interestingly, two chloroquinone-lipid alkoxyl conjugates were also detected and identified from the reaction between DCBQ and 13-HPODE. Analogous results were observed with other halogenated quinones. This represents the first report that halogenated quinoid carcinogens can enhance the decomposition of the endogenous lipid hydroperoxide 13-HPODE and formation of reactive lipid alkyl radicals and genotoxic HNE via a novel metal-independent nucleophilic substitution coupled with homolytic decomposition mechanism, which may partly explain their potential genotoxicity and carcinogenicity.