Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “pathological image”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 recordsLinked to original sources
PubMed2026

Digital pathology, image analysis, and artificial intelligence in liver disease.

Advances in digital pathology, image analysis, and artificial intelligence (AI) are rapidly transforming how pathologists and researchers interact with tissue samples and enable the development of diagnostic tools that harness high-resolution whole-slide images; these advances are in turn creating new opportunities for research, education, and routine clinical care globally. Liver disease is no exception, and digital pathology and AI have many applications in the diagnosis of liver cancer and liver diseases and in the assessment and management of transplantation. Although quantitative image analysis techniques have been applied to liver disease in research settings for over 50 years, recent improvements in image resolution, data storage, and the availability of advanced AI methods such as deep learning have driven multiple exciting developments. In this Review, we summarise the advancements in digital pathology, image analysis, and AI in liver disease. Key challenges such as access to and the logistics of using digital solutions, quality issues, and appropriate guidance in research and clinical use are reviewed, along with potential solutions to these challenges in the context of liver pathology and liver disease. Digital technologies are well established in liver pathology research, and access in clinical practice is increasing, with potential to address current laboratory challenges. Further evaluation is required to assess real-world effectiveness, clinical safety, and implementation of AI tools in liver pathology.

Journal Article↗
PubMed2026

GICPIdb: an archival repository of multimodal data focusing on pathological images for gastrointestinal cancers.

INTRODUCTION: Deep learning (DL) shows great potential for predicting biomarkers from routine histopathological slides of gastrointestinal (GI) cancers. Yet most existing models are validated on limited patient cohorts, while pathological image annotation and molecular marker standardization demand substantial professional expertise. To address these gaps, we constructed the Gastrointestinal Cancer Pathological Image Archive (GICPIdb, gicpidb.shubuzuo.top), a dedicated database and web platform covering seven major GI cancer types. METHODS: High-quality hematoxylin and eosin (H&E)-stained whole-slide images were collected from multiple sources and uniformly processed. Image annotations were performed by board-certified pathologists following standardized protocols. GICPIdb offers five interactive web modules for data uploading, quality control, feature extraction, online annotation and AI-based prediction. Its intuitive interface supports data browsing, retrieval, visualization and downloading. RESULTS: The database houses 2,863 pathologist-annotated, uniformly processed, high-quality H&E stained images collected from 2,655 patients. Of these, 1,699 patients were sourced from The Cancer Genome Atlas (TCGA), 182 from the Clinical Proteomic Tumor Analysis Consortium (CPTAC), and 424 from China-Japan Friendship Hospital and 350 from Chifeng Municipal Hospital in Inner Mongolia, China. It also integrates data on over 50 key molecular markers (e.g., MSI, TMB) and prognostic labels related to survival, recurrence and metastasis. DISCUSSION: GICPIdb aims to promote the development of DL-driven AI tools for cancer research and clinical translation. The multi-institutional data collection and standardized annotation pipeline are expected to enhance the generalizability and reproducibility of AI-based prediction models across diverse patient populations.

deep learning↗
PubMed2025

Bayesian Modeling of Cancer Outcomes Using Genetic Variables Assisted by Pathological Imaging Data.

With the increasing maturity of genetic profiling, an essential and routine task in cancer research is to model disease outcomes/phenotypes using genetic variables. Many methods have been successfully developed. However, oftentimes, empirical performance is unsatisfactory because of a "lack of information." In cancer research and clinical practice, a source of information that is broadly available and highly cost-effective comes from pathological images, which are routinely collected for definitive diagnosis and staging. In this article, we consider a Bayesian approach for selecting relevant genetic variables and modeling their relationships with a cancer outcome/phenotype. We propose borrowing information from (manually curated, low-dimensional) pathological imaging features via reinforcing the same selection results for the cancer outcome and imaging features. We further develop a weighting strategy to accommodate the scenario where information borrowing may not be equally effective for all subjects. Computation is carefully examined. Simulations demonstrate competitive performance of the proposed approach. We analyze TCGA (The Cancer Genome Atlas) LUAD (lung adenocarcinoma) data, with overall survival and gene expressions being the outcome and genetic variables, respectively. Findings different from the alternatives and with sound properties are made.

Humans↗
PubMedDate not supplied

[Attitude toward patients with pulmonary pathological images supposed to be tuberculosis but without bacteriological confirmation].

In view of establishing an attitude toward patients with pathological pulmonary images, suspected of tuberculosis but without bacteriological confirmation, a study was organized in an area serviced by 9 offices of phthisiology. A total of 154 such cases were identified between 1st January and 30th April 1978. These were followed up and controlled by radiological as well as bacteriological examinations for a period of one year. The anti-tuberculous treatment did not have to be applied except when the diagnosis was confirmed as tuberculosis. In 11 of the patients (7,1%) the diagnosis was made from the start, and it was established that they had active, non-bacillary pulmonary tuberculosis. In another 49 patients (31,8%) the suspicion was abandoned, and tuberculosis. In another 49 patients (31,8%) the suspicion was abandoned, and various other pulmonary affections, but not tuberculosis, were diagnosed, either of chronic or acute type. The remaining 94 patients (61,1%) remained suspected of tuberculosis. In 16 of them, in spite of the provisions made in the protocol of the study, anti-tuberculous treatment was applied. Of them 3 died of pulmonary cancers during the follow-up. The remaining suspects were not treated. Five of them (7,3%) have developed active tuberculosis, bacteriologically confirmed in 3 of the cases. The rest had a normal eventless evolution. The authors consider the careful investigation and follow-up of suspects for a period of one year as the most correct attitude in such cases.

Adolescent↗
PubMed1986

Small renal neoplasms: diagnostic imaging, pathologic features, and clinical course.

We retrospectively studied nine patients with solitary renal neoplasms that were first visible when smaller than 3 cm in diameter to determine their imaging and pathologic characteristics and clinical course. These neoplasms represented 14% of the total renal neoplasms discovered over a 6-year period, and only one-third were initially identified by screening urography. While seven of the patients had hematuria, most had associated urologic conditions (calculi, prostatism). Two patients had widespread metastases 2 and 4 years after the carcinomas first appeared. The remaining seven patients are alive and well 8 months to 6 years after undergoing nephrectomy, despite the significant delayed diagnosis in three patients. Only one lesion was pathologically benign (an oncocytoma). Two of the renal cell carcinomas were found within the walls of partially calcified renal cysts. Two (22%) of nine neoplasms exhibited aggressive biologic behavior, which suggests that these lesions may have greater metastatic potential than previously thought. We suggest that computed tomography be performed after screening urography and cystoscopy when unexplained hematuria is present.

Adenocarcinoma↗
PubMed1982

Correlation of an abnormal rest 201T1 myocardial image: pathological findings in cardiac transplant recipients.

Rest myocardial 201T1 scintigraphy was undertaken in 15 males mean age 39 years (22-54) who had been accepted for cardiac transplantation. Complete pathological correlation was obtained in 14 after transplantation and in 1 who died before a suitable donor heart became available. The average time from scintigraphy to pathological evaluation was 42 days (9-103). All the 201T1 images were grossly abnormal and on the basis of these studies it was not possible to differentiate ischemic from idiopathic cardiomyopathy. Each of the three views of the 201T1 study was divided into three segments, therefore 135 areas were available for comparison (3 x 3 x 15). Eighty-eight of these were abnormal on scan and 78 of these were abnormal pathologically. The right ventricle was seen on all rest images but the degree of uptake bore no relationship to the measured thickness of the right ventricular wall. Structures such as the atrial wall and the enlarged papillary muscle were visualized in some patients. In two patients there was an improvement of the rest 201T1 image in delayed views and histologically these areas showed a mixture of muscle and fibrous tissue. The sensitivity of 201T1 imaging in this study was 89% and there was close correlation of the images with gross and microscopic pathological findings.

Adult↗
PubMed1989

[Echography in studying the hyothyroepiglottic space. Normal image. Pathologic aspects. Histologic correlations].

Invasion of the hyothyroepiglottic (HTE) space, or pre-epiglottic space, constitutes an important element in selecting the type of therapy in cancer of the larynx (functional surgery, radiotherapy), the oropharynx and the hypopharynx. Clinical examination and standard X-ray films provide insufficient information. High frequency real time ultrasonography offers a reliable means for exploring the pre-epiglottic space, as evidenced by this study carried on 34 histologically-confirmed cases taken among 77 cases of carcinoma of the upper digestive and respiratory tracts. Advantages presented by this method over CT-scanning and MR imaging in this particular pathological are simplicity, rapidity and low cost, combined with good performance.

Humans↗
PubMed1991

High-signal-intensity rim surrounding uterine leiomyomas on MR images: pathologic correlation.

A high-intensity rim surrounding uterine leiomyomas was identified on T2-weighted magnetic resonance (MR) images in five of 13 patients with histopathologically confirmed leiomyomas. These peripheral high-intensity rims were not associated with subject age or with size, location, or degeneration of the leiomyomas. Histologic examination revealed markedly dilated lymphatic vessels, dilated veins, edema, or a combination of these features to correspond to the location of the high-intensity rims. These benign causes of high intensity in the myometrium should not be confused with clinically important processes such as adenomyosis or invasion by endometrial carcinoma.

Adult↗
PubMed1989

Function within mesoblastic nephroma: imaging--pathologic correlation.

Congenital mesoblastic nephroma is the only primary renal neoplasm with radiographically demonstrable function. Renal function within two typical congenital mesoblastic nephromas was demonstrated by computed tomography in one case and renal scintigraphy in the other. Excretion of contrast medium and radionuclide was due to functioning nephrons trapped within the tumor.

Female↗
PubMed1985

[Thrombosis of the umbilical vein in the ultrasound image--pathological findings and review of the literature].

The authors present a case of thrombosis of the umbilical vein in a foetus in the 27th week of pregnancy, discovered via ultrasound diagnosis. The foetus presented with marked ascites and anasarca. Despite foetal death there were no visceral malformations, and no pathological criteria presented by the mother. The characteristic features and sensitivity of sonographic diagnosis in umbilical vein thromboses are discussed as part of the extensive pathology of the umbilical cord.

Adult↗
PubMed1992

Hepatic parenchymal perfusion defects detected with CTAP: imaging-pathologic correlation.

To determine whether characteristics of focal hepatic parenchymal perfusion defects detected with computed tomographic arterial portography (CTAP) correlate with underlying pathologic processes, 245 perfusion defects detected with CTAP in 60 patients who subsequently underwent definitive hepatic surgery were characterized by shape, location within the liver, and relative attenuation value and were prospectively correlated with sectioned pathologic specimens. Of 177 round perfusion defects, 102 (58%) were malignant and 75 (42%) were benign. Only one (2%) of 53 peripheral wedge-shaped defects was malignant. All 15 peripheral flat defects were benign. Defects in characteristic locations anterior to the porta hepatis (n = 15) and adjacent to the intersegmental fissure (n = 7) were uniformly benign. While 83 (56%) of 147 soft-tissue attenuation defects were malignant, only four (6%) of 68 intermediate-attenuation defects were malignant. Although these characteristics of parenchymal perfusion defects aid in differentiation of benign from malignant processes, all other types of perfusion defects are nonspecific and may require biopsy.

Adenoma, Bile Duct↗
PubMed1987

[Prostatic pathology imaged by magnetic resonance. 58 cases].

Forty-eight patients with prostatic disease (benign prostatic hyperplasia (B.P.H.), carcinoma, cysts, myoma and prostatitis) and 10 normal volunteers underwent magnetic resonance imaging (M.R.I.) of the prostate. The prostatic parenchyma was best evaluated by a T2-weighted spin-echo pulse sequence. The prostate in patients with B.P.H. often had a homogeneous or more rarely a nodular appearance on T2-weighted images. In most cases, a peripheral dark rim is observed. All prostate in patients with carcinoma had an heterogeneous appearance on T2-weighted images. While most of the prostatic carcinomas appeared hypo-intense relative to adjacent prostatic parenchyma, some of the neoplasms had a high or mixed-high and low signal. The myoma showed a low-signal nodule like carcinoma. The cyst appears as a liquid tumor. The prostatitis had an homogeneous bright signal. With the used methodology, MRI can differentiate prostatic diseases in many cases. Nevertheless the technique has to be optimized to improve its accuracy.

Cysts↗
PubMed1992

Chondrosarcoma: MR imaging with pathologic correlation.

Magnetic resonance (MR) images of 21 surgically confirmed chondrosarcomas were retrospectively reviewed in conjunction with plain radiographs and computed tomographic scans and correlated with pathologic findings. The tumors appeared lobulated, and signal intensity, as analyzed visually (intermediate on T1-weighted, high on T2-weighted images), was similar for all lesions, regardless of pathologic type. Size of lesion was not an indicator of grade. The appearances of mesenchymal and dedifferentiated chondrosarcomas mimicked that of conventional chondrosarcoma. Extraskeletal chondrosarcoma was visualized as a lobulated soft-tissue mass. In all cases, MR imaging accurately depicted intraosseous and soft-tissue extent of tumor noted at surgery and pathologic examination. Histologic type or grade of chondrosarcoma generally cannot be characterized on the basis of visual analysis of signal intensity noted on routine MR images. However, MR imaging is excellent for exact delineation of tumor extent.

Bone Neoplasms↗