Differential diagnosis of thyroid nodule capsules using random forest guided selection of image features.

Microscopic evaluation of tissue sections stained with hematoxylin and eosin is the current gold standard for diagnosing thyroid pathology. Digital pathology is gaining momentum providing the pathologist with additional cues to traditional routes when placing a diagnosis, therefore it is extremely important to develop new image analysis methods that can extract image features with diagnostic potential. In this work, we use histogram and texture analysis to extract features from microscopic images acquired on thin thyroid nodule capsules sections and demonstrate how they enable the differential diagnosis of thyroid nodules. Targeted thyroid nodules are benign (i.e., follicular adenoma) and malignant (i.e., papillary thyroid carcinoma and its sub-type arising within a follicular adenoma). Our results show that the considered image features can enable the quantitative characterization of the collagen capsule surrounding thyroid nodules and provide an accurate classification of the latter's type using random forest.

PSHG-TISS: A collection of polarization-resolved second harmonic generation microscopy images of fixed tissues.

Second harmonic generation (SHG) microscopy is acknowledged as an established imaging technique capable to provide information on the collagen architecture in tissues that is highly valuable for the diagnostics of various pathologies. The polarization-resolved extension of SHG (PSHG) microscopy, together with associated image processing methods, retrieves extensive image sets under different input polarization settings, which are not fully exploited in clinical settings. To facilitate this, we introduce PSHG-TISS, a collection of PSHG images, accompanied by additional computationally generated images which can be used to complement the subjective qualitative analysis of SHG images. These latter have been calculated using the single-axis molecule model for collagen and provide 2D representations of different specific PSHG parameters known to account for the collagen structure and distribution. PSHG-TISS can aid refining existing PSHG image analysis methods, while also supporting the development of novel image processing and analysis methods capable to extract meaningful quantitative data from the raw PSHG image sets. PSHG-TISS can facilitate the breadth and widespread of PSHG applications in tissue analysis and diagnostics.

Assessment of Extramammary Paget Disease by Two-Photon Microscopy.

Two-photon microscopy techniques are non-linear optical imaging methods which are gaining momentum in the investigation of fixed tissue sections, fresh tissue or even for in vivo experiments. Two-photon excited fluorescence and second harmonic generation are two non-linear optical contrast mechanisms which can be simultaneously used for offering complementary information on the tissue architecture. While the former can originate from endogenous autofluorescence sources (e.g., NADH, FAD, elastin, keratin, lipofuscins, or melanin), or exogenous eosin, the latter is generated in fibrillar structures within living organisms (e.g., collagen and myosin). Here we test the ability of both these contrast mechanisms to highlight features of the extramammary Paget disease on fixed tissue sections prepared for standard histological examination using immunohistochemical markers and hematoxylin and eosin staining. We also demonstrate the label-free abilities of both imaging techniques to highlight histological features on unstained fixed tissue sections. The study demonstrated that two-photon microscopy can detect specific cellular features of the extramammary Paget disease in good correlation with histopathological results.

Pixel-level angular quantification of capsular collagen in second harmonic generation microscopy images of encapsulated thyroid nodules.

Polarization-resolved second harmonic generation microscopy is used to provide pixel-level angular distribution of collagen in thyroid nodule capsules. The pixel-level angular distribution is combined with textural analysis to quantify the collagen distribution in follicular adenoma (benign) and papillary thyroid carcinoma (malignant). Three second order nonlinear susceptibility tensor elements ratios, the collagen angular distribution and two parameters accounting for the collagen angular dispersion in different sized areas are extracted and corresponding images are computed in a pixel-by-pixel fashion. Subsequently, we show that texture analysis can be performed on these images to detect significant differences between the considered benign and malignant nodule capsules.

Quantitative second harmonic generation microscopy for the structural characterization of capsular collagen in thyroid neoplasms.

Quantitative second harmonic generation microscopy was used to investigate collagen organization in the fibrillar capsules of human benign and malignant thyroid nodules. We demonstrate that the combination of texture analysis and second harmonic generation images of collagen can be used to differentiate between capsules surrounding the thyroid follicular adenoma and papillary carcinoma nodules. Our findings indicate that second harmonic generation microscopy can provide quantitative information about the collagenous capsule surrounding both the thyroid and thyroid nodules, which may complement traditional histopathological examination.