Objective:
The microscopic analysis of biopsied lung nodules represents the gold-standard for definitive diagnosis of lung cancer. Deep learning has achieved pathologist-level classification of ...non-small cell lung cancer histopathology images at high resolutions (0.5–2 µm/px), and recent studies have revealed tomography–histology relationships at lower spatial resolutions. Thus, we tested whether patterns for histological classification of lung cancer could be detected at spatial resolutions such as those offered by ultra-high-resolution CT.
Methods:
We investigated the performance of a deep convolutional neural network (inception-v3) to classify lung histopathology images at lower spatial resolutions than that of typical pathology. Models were trained on 2167 histopathology slides from The Cancer Genome Atlas to differentiate between lung cancer tissues (adenocarcinoma (LUAD) and squamous-cell carcinoma (LUSC)), and normal dense tissue. Slides were accessed at 2.5 × magnification (4 µm/px) and reduced resolutions of 8, 16, 32, 64, and 128 µm/px were simulated by applying digital low-pass filters.
Results:
The classifier achieved area under the curve ≥0.95 for all classes at spatial resolutions of 4–16 µm/px, and area under the curve ≥0.95 for differentiating normal tissue from the two cancer types at 128 µm/px.
Conclusions:
Features for tissue classification by deep learning exist at spatial resolutions below what is typically viewed by pathologists.
Advances in knowledge:
We demonstrated that a deep convolutional network could differentiate normal and cancerous lung tissue at spatial resolutions as low as 128 µm/px and LUAD, LUSC, and normal tissue as low as 16 µm/px. Our data, and results of tomography–histology studies, indicate that these patterns should also be detectable within tomographic data at these resolutions.
The 2021 World Health Organization (WHO) Classification of Tumors of the Central Nervous System (CNS) and recent smaller annual updates have shown that alterations in tumor genetics are essential to ...determining tumor diagnosis, biological activity, and potential treatment options. This review summarizes the most important mutations and oncometabolites, with a focus on the central role played by 2-hydroxyglutarate in isocitrate dehydrogenase mutant tumors, as well as their corresponding imaging counterparts using standard and advanced imaging techniques.
Vulvar and vaginal lesions representing a wide spectrum of diseases in female lower genital tract diseases make up a small part of all gynecological etiologies. Many of them are rare etiologies and ...are reported in case-reports studies. Translabial and transperineal ultrasound are modalities of choice for the first evaluation of perineal lesions. MRI is usually performed to determine the etiology of the lesions and stage. Benign lesions of the vulva and vagina usually manifest as simple cystic (vestibular cyst or endometrioma) or solid lesions (leiomyoma or angiofibroblastoma), while malignancies usually appear as large, solid masses and fill into both vaginal and perineal area. Post-contrast images play an important role in establishing a differential diagnosis, however, some benign lesions can also exhibit a vivid enhancement. Knowledge about radiologic-associated pathological manifestations may aid clinicians in better understanding these pathologies, especially for some rare lesions, and making a proper diagnosis before invasive procedures.
In recent years, researchers have explored new ways to obtain information from pathological tissues, also exploring non-invasive techniques, such as virtual biopsy (VB). VB can be defined as a test ...that provides promising outcomes compared to traditional biopsy by extracting quantitative information from radiological images not accessible through traditional visual inspection. Data are processed in such a way that they can be correlated with the patient's phenotypic expression, or with molecular patterns and mutations, creating a bridge between traditional radiology, pathology, genomics, and artificial intelligence (AI). Radiomics is the backbone of VB, since it allows the extraction and selection of features from radiological images, feeding them into AI models in order to derive lesions' pathological characteristics and molecular status. Presently, the output of VB provides only a gross approximation of the findings of tissue biopsy. However, in the future, with the improvement of imaging resolution and processing techniques, VB could partially substitute the classical surgical or percutaneous biopsy, with the advantage of being non-invasive, comprehensive, accounting for lesion heterogeneity, and low cost. In this review, we investigate the concept of VB in abdominal pathology, focusing on its pipeline development and potential benefits.
Proton therapy has a theoretical dosimetric advantage due to the Bragg peak, but the linear energy transfer (LET), and therefore the relative biological effectiveness (RBE), increase at the end of ...range. For patients with Hodgkin lymphoma, the distal edge of beam is often located within or close to the heart, where elevated RBE would be of potential concern. The purpose of this study was to investigate the impact of RBE and the choice of beam arrangement for adolescent patients with mediastinal Hodgkin lymphoma.
For three previously treated adolescent patients, proton plans with 1-3 fields were created to a prescribed dose of 19.8 Gy (RBE) in 11 fractions (Varian Eclipse v13.7), assuming an RBE of 1.1. Plans were recalculated using Monte-Carlo (Geant4 v10.3.3/Gate v8.1) to calculate dose-averaged LET. Variable RBE-weighted dose was calculated using the McNamara model, assuming an α/β ratio of 2 Gy for organs-at-risk.
Although the LET decreased as the number of fields increased, the difference in RBE-weighted dose (Δdose) to organs-at-risk did not consistently decrease. Δdose values varied by patient and organ and were mostly of the order of 0-3 Gy (RBE), with a worst-case of 4.75 Gy (RBE) in near-maximum dose to the left atrium for one plan.
RBE-weighted doses to organs-at-risk are sensitive to the choice of RBE model, which is of particular concern for the heart.
There is a need to remain cautious when evaluating proton plans for Hodgkin lymphoma, especially when near-maximum doses to organs-at-risk are considered.
The origin of pseudomyxoma peritoneii (PMP) has been established as low-grade appendiceal mucinous tumors (AMT). However, intestinal-type ovarian mucinous tumors are known as another source of PMP. ...Recently, it is advocated that ovarian mucinous tumors causing PMP originates from teratomas. However, AMTs are often too small to detect on imaging; then, differentiating metastatic ovarian tumors of AMT from ovarian teratoma-associated mucinous tumors (OTAMT) is important. Therefore, this study investigates the MR characteristics of OTAMT compared to the ovarian metastasis of AMT.
MR findings of six pathologically confirmed OTAMT were retrospectively analyzed compared to ovarian metastases of low-grade appendiceal mucinous neoplasms (LAMN). We studied the existence of PMP, uni- or bilateral disease, the maximum diameter of ovarian masses, the number of loculi, a variety of sizes and signal intensity of each content, the existence of the solid part, fat, calcification within the mass, and appendiceal diameters. All the findings were statistically analyzed using the Mann-Whitney test.
Four of the six OTAMT showed PMP. OTAMT showed unilateral disease, had a larger diameter, more frequent intratumoral fat, smaller appendiceal diameter than those in AMT, and they were statistically significant (
< .05). On the other hand, the number, variety of size, signal intensity of loculi, and the solid part, calcification within the mass did not differ from each other.
Both OTAMT and ovarian metastasis of AMT appeared as multilocular cystic masses with relatively uniform signal and size of loculi. However, a larger unilateral disease with intratumoral fat and smaller size of the appendix may suggest OTAMT.
OTAMT can be another source of PMP, as AMT. MR characteristics of OTAMT were very similar to ovarian metastases of AMT; however, in cases with PMP combined with fat-containing multilocular cystic ovarian mass, we can diagnose them as OTAMT, not PMP caused by AMT.
The first patient was misclassified in the diagnostic conclusion according to a local clinical expert opinion in a new clinical implementation of a knee osteoarthritis artificial intelligence (AI) ...algorithm at Bispebjerg-Frederiksberg University Hospital, Copenhagen, Denmark. In preparation for the evaluation of the AI algorithm, the implementation team collaborated with internal and external partners to plan workflows, and the algorithm was externally validated. After the misclassification, the team was left wondering: what is an acceptable error rate for a low-risk AI diagnostic algorithm? A survey among employees at the Department of Radiology showed significantly lower acceptable error rates for AI (6.8 %) than humans (11.3 %). A general mistrust of AI could cause the discrepancy in acceptable errors. AI may have the disadvantage of limited social capital and likeability compared to human co-workers, and therefore, less potential for forgiveness. Future AI development and implementation require further investigation of the fear of AI's unknown errors to enhance the trustworthiness of perceiving AI as a co-worker. Benchmark tools, transparency, and explainability are also needed to evaluate AI algorithms in clinical implementations to ensure acceptable performance.
Cutaneous lesions are derived from the epidermis, dermis and cutaneous appendages. Whilst imaging may occasionally be performed to evaluate such lesions, they may be undiagnosed and demonstrated for ...the first time on head and neck imaging studies. Although usually amenable to clinical examination and biopsy, CT or MRI studies may also demonstrate characteristic imaging features which aid the radiological differential diagnosis. In addition, imaging studies define the extent and staging of malignant lesions, as well as the complications of benign lesions. It is important for the radiologist to understanding the clinical significance and associations of these cutaneous conditions. This pictorial review will describe and depict the imaging appearances of benign, malignant, overgrowth, blistering, appendage and syndromic cutaneous lesions. An increasing awareness of the imaging characteristics of cutaneous lesions and related conditions will help the framing of a clinically relevant report.
The main objective of this work was to detect novel biomarkers in breast cancer by spreading the MR spectra over two dimensions in multiple spatial locations using an accelerated 5D EP-COSI ...technology.
The 5D EP-COSI data were non-uniformly undersampled with an acceleration factor of 8 and reconstructed using group sparsity-based compressed sensing reconstruction. Different metabolite and lipid ratios were then quantified and statistically analyzed for significance. Linear discriminant models based on the quantified metabolite and lipid ratios were generated. Spectroscopic images of the quantified metabolite and lipid ratios were also reconstructed.
The 2D COSY spectra generated using the 5D EP-COSI technique showed differences among healthy, benign, and malignant tissues in terms of their mean values of metabolite and lipid ratios, especially the ratios of potential novel biomarkers based on unsaturated fatty acids, myo-inositol, and glycine. It is further shown the potential of choline and unsaturated lipid ratio maps, generated from the quantified COSY signals across multiple locations in the breast, to serve as complementary markers of malignancy that can be added to the multiparametric MR protocol. Discriminant models using metabolite and lipid ratios were found to be statistically significant for classifying benign and malignant tumor from healthy tissues.
Accelerated 5D EP-COSI technique demonstrates the potential to detect novel biomarkers such as glycine, myo-inositol, and unsaturated fatty acids in addition to commonly reported choline in breast cancer, and facilitates metabolite and lipid ratio maps which have the potential to play a significant role in breast cancer detection.
This study presents the first evaluation of a multidimensional MR spectroscopic imaging technique for the detection of potentially novel biomarkers based on glycine, myo-inositol, and unsaturated fatty acids, in addition to commonly reported choline. Spatial mapping of choline and unsaturated fatty acid ratios with respect to water in malignant and benign breast masses are also shown. These metabolic characteristics may serve as additional biomarkers for improving the diagnostic and therapeutic evaluation of breast cancer.
