-
Journal of Clinical Medicine Oct 2023Renal biopsies are the gold standard for diagnosis, staging, and prognosis of underlying parenchymal kidney disease. This article provides an overview of the current... (Review)
Review
Renal biopsies are the gold standard for diagnosis, staging, and prognosis of underlying parenchymal kidney disease. This article provides an overview of the current indications and highlights ways to reduce bleeding complications in order to achieve optimal diagnostic yield with minimal risk to the patient. Novel indications have emerged from the increasing use of new molecularly targeted oncologic therapies in recent years, which often induce immune-mediated renal disease. On the other hand, the detection of specific antibodies against target antigens on podocytes in the sera of patients with new-onset nephrotic syndrome has now relativized the indication for biopsy in membranous nephropathy. The use of semi-automatic spring-loaded biopsy devices and real-time ultrasound considerably declined the complication rate and is the current standard. Percutaneous renal biopsies are overall a safe procedure if contraindications are considered. A coagulation disorder needs to be excluded beforehand, and an elevated blood pressure must be reduced to the normotensive range with medications. A laparoscopic approach or a radiology interventional procedure through the internal jugular vein may be considered for obtaining a kidney tissue sample if there is an urgent indication and a bleeding tendency cannot be adequately corrected. Major bleeding after a percutaneous renal biopsy can usually be managed with selective arterial embolization of the injured renal vessel. The use of a 16-gauge needle is the most reasonable compromise between diagnostic benefit and risk of complication. In the routine diagnostic, the biopsy specimen is examined with light microscopy, immunohistochemistry, and electron microscopy. Combination with modern molecular pathology techniques will contribute to more precise insights into the development and progression of kidney disease, which will likely refine future treatments in nephrology.
PubMed: 37835066
DOI: 10.3390/jcm12196424 -
Cancer Cell Sep 2023Deep learning (DL) can accelerate the prediction of prognostic biomarkers from routine pathology slides in colorectal cancer (CRC). However, current approaches rely on...
Deep learning (DL) can accelerate the prediction of prognostic biomarkers from routine pathology slides in colorectal cancer (CRC). However, current approaches rely on convolutional neural networks (CNNs) and have mostly been validated on small patient cohorts. Here, we develop a new transformer-based pipeline for end-to-end biomarker prediction from pathology slides by combining a pre-trained transformer encoder with a transformer network for patch aggregation. Our transformer-based approach substantially improves the performance, generalizability, data efficiency, and interpretability as compared with current state-of-the-art algorithms. After training and evaluating on a large multicenter cohort of over 13,000 patients from 16 colorectal cancer cohorts, we achieve a sensitivity of 0.99 with a negative predictive value of over 0.99 for prediction of microsatellite instability (MSI) on surgical resection specimens. We demonstrate that resection specimen-only training reaches clinical-grade performance on endoscopic biopsy tissue, solving a long-standing diagnostic problem.
Topics: Humans; Algorithms; Biomarkers; Biopsy; Microsatellite Instability; Colorectal Neoplasms
PubMed: 37652006
DOI: 10.1016/j.ccell.2023.08.002 -
EBioMedicine Aug 2023For patients with early-stage breast cancers, neoadjuvant treatment is recommended for non-luminal tumors instead of luminal tumors. Preoperative distinguish between...
Deep learning radiopathomics based on preoperative US images and biopsy whole slide images can distinguish between luminal and non-luminal tumors in early-stage breast cancers.
BACKGROUND
For patients with early-stage breast cancers, neoadjuvant treatment is recommended for non-luminal tumors instead of luminal tumors. Preoperative distinguish between luminal and non-luminal cancers at early stages will facilitate treatment decisions making. However, the molecular immunohistochemical subtypes based on biopsy specimens are not always consistent with final results based on surgical specimens due to the high intra-tumoral heterogeneity. Given that, we aimed to develop and validate a deep learning radiopathomics (DLRP) model to preoperatively distinguish between luminal and non-luminal breast cancers at early stages based on preoperative ultrasound (US) images, and hematoxylin and eosin (H&E)-stained biopsy slides.
METHODS
This multicentre study included three cohorts from a prospective study conducted by our team and registered on the Chinese Clinical Trial Registry (ChiCTR1900027497). Between January 2019 and August 2021, 1809 US images and 603 H&E-stained whole slide images (WSIs) from 603 patients with early-stage breast cancers were obtained. A Resnet18 model pre-trained on ImageNet and a multi-instance learning based attention model were used to extract the features of US and WSIs, respectively. An US-guided Co-Attention module (UCA) was designed for feature fusion of US and WSIs. The DLRP model was constructed based on these three feature sets including deep learning US feature, deep learning WSIs feature and UCA-fused feature from a training cohort (1467 US images and 489 WSIs from 489 patients). The DLRP model's diagnostic performance was validated in an internal validation cohort (342 US images and 114 WSIs from 114 patients) and an external test cohort (270 US images and 90 WSIs from 90 patients). We also compared diagnostic efficacy of the DLRP model with that of deep learning radiomics model and deep learning pathomics model in the external test cohort.
FINDINGS
The DLRP yielded high performance with area under the curve (AUC) values of 0.929 (95% CI 0.865-0.968) in the internal validation cohort, and 0.900 (95% CI 0.819-0.953) in the external test cohort. The DLRP also outperformed deep learning radiomics model based on US images only (AUC 0.815 [0.719-0.889], p = 0.027) and deep learning pathomics model based on WSIs only (AUC 0.802 [0.704-0.878], p = 0.013) in the external test cohort.
INTERPRETATION
The DLRP can effectively distinguish between luminal and non-luminal breast cancers at early stages before surgery based on pretherapeutic US images and biopsy H&E-stained WSIs, providing a tool to facilitate treatment decision making in early-stage breast cancers.
FUNDING
Natural Science Foundation of Guangdong Province (No. 2023A1515011564), and National Natural Science Foundation of China (No. 91959127; No. 81971631).
Topics: Humans; Female; Breast Neoplasms; Deep Learning; Prospective Studies; Biopsy; Ultrasonography
PubMed: 37478528
DOI: 10.1016/j.ebiom.2023.104706 -
Archives of Pathology & Laboratory... Apr 2024Myelodysplasia cutis is an emerging concept in cutaneous neoplasia. Many of these cases were previously included under the umbrella of histiocytoid Sweet syndrome.... (Review)
Review
CONTEXT.—
Myelodysplasia cutis is an emerging concept in cutaneous neoplasia. Many of these cases were previously included under the umbrella of histiocytoid Sweet syndrome. However, with the advent of next-generation sequencing, cutaneous involvement by myelodysplastic syndrome is being increasingly recognized.
OBJECTIVE.—
To review histiocytoid Sweet syndrome and myelodysplasia cutis and discuss our current understanding of these entities. Additionally, to discuss how next-generation sequencing can be applied in the evaluation of cutaneous infiltrates of immature histiocytoid cells.
DATA SOURCES.—
The English-language literature from 2005 to 2023 on the topic of histiocytoid Sweet syndrome and myelodysplasia cutis was reviewed.
CONCLUSIONS.—
Biopsy specimens showing infiltrates of histiocytoid, immature myeloid cells may represent cutaneous involvement by myelodysplastic syndrome. Close clinical correlation is recommended in these cases. Recent studies suggest that next-generation sequencing is useful in separating myelodysplasia cutis from true histiocytoid Sweet syndrome. This distinction has important implications for patients.
Topics: Humans; Myelodysplastic Syndromes; Skin; Skin Neoplasms; Sweet Syndrome
PubMed: 37787422
DOI: 10.5858/arpa.2023-0132-RA -
International Journal of Molecular... Jun 2023Tissue biopsy is essential for NSCLC diagnosis and treatment management. Over the past decades, liquid biopsy has proven to be a powerful tool in clinical oncology,... (Review)
Review
Tissue biopsy is essential for NSCLC diagnosis and treatment management. Over the past decades, liquid biopsy has proven to be a powerful tool in clinical oncology, isolating tumor-derived entities from the blood. Liquid biopsy permits several advantages over tissue biopsy: it is non-invasive, and it should provide a better view of tumor heterogeneity, gene alterations, and clonal evolution. Consequentially, liquid biopsy has gained attention as a cancer biomarker tool, with growing clinical applications in NSCLC. In the era of precision medicine based on molecular typing, non-invasive genotyping methods became increasingly important due to the great number of oncogene drivers and the small tissue specimen often available. In our work, we comprehensively reviewed established and emerging applications of liquid biopsy in NSCLC. We made an excursus on laboratory analysis methods and the applications of liquid biopsy either in early or metastatic NSCLC disease settings. We deeply reviewed current data and future perspectives regarding screening, minimal residual disease, micrometastasis detection, and their implication in adjuvant and neoadjuvant therapy management. Moreover, we reviewed liquid biopsy diagnostic utility in the absence of tissue biopsy and its role in monitoring treatment response and emerging resistance in metastatic NSCLC treated with target therapy and immuno-therapy.
Topics: Humans; Lung Neoplasms; Carcinoma, Non-Small-Cell Lung; Liquid Biopsy; Biopsy; Precision Medicine; Biomarkers, Tumor
PubMed: 37445976
DOI: 10.3390/ijms241310803 -
Frontiers in Endocrinology 2023After the metabolic syndrome and its components, thyroid disorders represent the most common endocrine disorders, with increasing prevalence in the last two decades.... (Review)
Review
After the metabolic syndrome and its components, thyroid disorders represent the most common endocrine disorders, with increasing prevalence in the last two decades. Thyroid dysfunctions are distinguished by hyperthyroidism, hypothyroidism, or inflammation (thyroiditis) of the thyroid gland, in addition to the presence of thyroid nodules that can be benign or malignant. Thyroid cancer is typically detected an ultrasound (US)-guided fine-needle aspiration biopsy (FNAB) and cytological examination of the specimen. This approach has significant limitations due to the small sample size and inability to characterize follicular lesions adequately. Due to the rapid advancement of high-throughput molecular biology techniques, it is now possible to identify new biomarkers for thyroid neoplasms that can supplement traditional imaging modalities in postoperative surveillance and aid in the preoperative cytology examination of indeterminate or follicular lesions. Here, we review current knowledge regarding biomarkers that have been reliable in detecting thyroid neoplasms, making them valuable tools for assessing the efficacy of surgical procedures or adjunctive treatment after surgery. We are particularly interested in providing an up-to-date and systematic review of emerging biomarkers, such as mRNA and non-coding RNAs, that can potentially detect thyroid neoplasms in clinical settings. We discuss evidence for miRNA, lncRNA and circRNA dysregulation in several thyroid neoplasms and assess their potential for use as diagnostic and prognostic biomarkers.
Topics: Humans; Sensitivity and Specificity; Thyroid Nodule; Thyroid Neoplasms; Biomarkers
PubMed: 37547301
DOI: 10.3389/fendo.2023.1218320